Model save

README.md

@@ -0,0 +1,58 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: math-lora
+  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. -->
+
+# math-lora
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6782
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 512
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0     | 0    | 1.6782          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ab2d40757d64f0fcd70df52ae53610eb4487d8afb2022d6ad3d1a8f3fb2f08
+size 218138576

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0,
+    "eval_loss": 1.6781893968582153,
+    "eval_runtime": 1.9026,
+    "eval_samples": 100,
+    "eval_samples_per_second": 52.559,
+    "eval_steps_per_second": 6.833,
+    "train_loss": 0,
+    "train_runtime": 68.9963,
+    "train_samples": 1100,
+    "train_samples_per_second": 15.943,
+    "train_steps_per_second": 0.029
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0,
+    "eval_loss": 1.6781893968582153,
+    "eval_runtime": 1.9026,
+    "eval_samples": 100,
+    "eval_samples_per_second": 52.559,
+    "eval_steps_per_second": 6.833
+}

runs/Nov27_15-15-56_hpc-hblab/events.out.tfevents.1701072986.hpc-hblab.998006.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bd3b6737ead906d192567a5ba3f6711d780b0d6d91830bdcf94c876c1339c4
+size 7337

runs/Nov29_15-52-57_hpc-hblab/events.out.tfevents.1701248066.hpc-hblab.1391487.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fca52b4674efbe46da6f33649de9575d4c85d7e5ecc3623fc24243dfffc9343
+size 4494

runs/Nov29_16-00-52_hpc-hblab/events.out.tfevents.1701248543.hpc-hblab.1392562.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d1b03ca897c681e6a6eb3ecfaf0d62b275a702ea0ab8a9c830b1f4930bf385
+size 4485

runs/Nov29_17-16-48_hpc-hblab/events.out.tfevents.1701253096.hpc-hblab.1408066.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0a27c54ddca770f21d40986893a6b917f3be95c46dae749aa8a830846ed799
+size 4485

runs/Nov29_17-20-34_hpc-hblab/events.out.tfevents.1701253323.hpc-hblab.1409430.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20133b418f86e3f474079b1ef08789f7c8ce5e92016464c3538dd8e17568349f
+size 4485

runs/Nov29_17-24-08_hpc-hblab/events.out.tfevents.1701253533.hpc-hblab.1410000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71f247da6367ca19b8c989bec2f2a09a1424451e599ae428215494ed97e58d0
+size 4229

runs/Nov29_17-45-15_hpc-hblab/events.out.tfevents.1701254798.hpc-hblab.1414379.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0999c4d147f70f963dd933356c10c5bee0b136617f3d4a64e99ddc457dad391b
+size 4485

runs/Nov29_17-57-18_hpc-hblab/events.out.tfevents.1701255521.hpc-hblab.1416992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087d411b7fede443c205abefdbfaa67807ba7b89fec2076550ab4f2346857d75
+size 4485

runs/Nov30_08-14-28_hpc-hblab/events.out.tfevents.1701306954.hpc-hblab.1528715.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3e003011617dc3ad850c557004cf46c4a7d7d903d6f885f764ea5059c662c5
+size 4485

runs/Nov30_08-21-57_hpc-hblab/events.out.tfevents.1701307403.hpc-hblab.1529729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde428ea04b1e48fd4ed933af2d29c8292d8c5d1dc2d387cb18df69cffaf77df
+size 4821

runs/Nov30_08-21-57_hpc-hblab/events.out.tfevents.1701307474.hpc-hblab.1529729.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3c00212451bd99b651c63c2feb6b00182cf936bedec39679da6e816649fa58
+size 344

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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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": "{% 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": 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": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0,
+    "train_loss": 0,
+    "train_runtime": 68.9963,
+    "train_samples": 1100,
+    "train_samples_per_second": 15.943,
+    "train_steps_per_second": 0.029
+}

trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0,
+  "eval_steps": 500,
+  "global_step": 0,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 1.6781895160675049,
+      "eval_runtime": 1.9005,
+      "eval_samples_per_second": 52.619,
+      "eval_steps_per_second": 6.84,
+      "step": 0
+    },
+    {
+      "epoch": 0,
+      "step": 0,
+      "total_flos": 4138152939749376.0,
+      "train_loss": 0,
+      "train_runtime": 68.9963,
+      "train_samples_per_second": 15.943,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4138152939749376.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b794ac5ebe87d869f2f6a88f8400a90ee48517c4e6afe65a5e8e32fb1f3e1c4
+size 4664