Upload 12 files

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "davidkim205/komt-mistral-7b-v1",
+  "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": 16.0,
+  "lora_dropout": 0.3,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "gate_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 sha256:30c47692b44bd4c7757d7cdf249dd16ba4c2c363d0552e10495570c759fa49b9
+size 167832240

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c0d65913b54a76c7459e1e339996ec78ce9fb835ee412011bddd1a8d1cae10
+size 84571156

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+peft

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82314b98f8a55743027184d3df6336b209a6835850fe863b7b0a453e011dec5d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46836e4c761705209e1b953d5034dec441969c6b809e5711efb7febaa0d34e71
+size 1064

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "<unk>",
+  "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 +1,49 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,321 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9011406844106464,
+  "eval_steps": 50,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6337016224861145,
+      "learning_rate": 7.5e-07,
+      "loss": 1.326,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.3350285291671753,
+      "eval_runtime": 394.6138,
+      "eval_samples_per_second": 5.459,
+      "eval_steps_per_second": 0.684,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.6025093197822571,
+      "learning_rate": 1.5e-06,
+      "loss": 1.3065,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 1.2850024700164795,
+      "eval_runtime": 394.5243,
+      "eval_samples_per_second": 5.46,
+      "eval_steps_per_second": 0.684,
+      "step": 100
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.5091537237167358,
+      "learning_rate": 2.25e-06,
+      "loss": 1.2129,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 1.1226935386657715,
+      "eval_runtime": 394.4733,
+      "eval_samples_per_second": 5.46,
+      "eval_steps_per_second": 0.684,
+      "step": 150
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.6157342195510864,
+      "learning_rate": 3e-06,
+      "loss": 0.9817,
+      "step": 200
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.8010650873184204,
+      "eval_runtime": 394.6158,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 0.684,
+      "step": 200
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.22548706829547882,
+      "learning_rate": 2.971177920604846e-06,
+      "loss": 0.6524,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.5880268812179565,
+      "eval_runtime": 394.5715,
+      "eval_samples_per_second": 5.459,
+      "eval_steps_per_second": 0.684,
+      "step": 250
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.19589273631572723,
+      "learning_rate": 2.88581929876693e-06,
+      "loss": 0.5671,
+      "step": 300
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.563366174697876,
+      "eval_runtime": 394.434,
+      "eval_samples_per_second": 5.461,
+      "eval_steps_per_second": 0.685,
+      "step": 300
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.20705421268939972,
+      "learning_rate": 2.747204418453818e-06,
+      "loss": 0.5519,
+      "step": 350
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 0.547275722026825,
+      "eval_runtime": 394.6461,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 0.684,
+      "step": 350
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1976100355386734,
+      "learning_rate": 2.5606601717798212e-06,
+      "loss": 0.5389,
+      "step": 400
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.5334580540657043,
+      "eval_runtime": 394.6493,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 0.684,
+      "step": 400
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.18715547025203705,
+      "learning_rate": 2.3333553495294033e-06,
+      "loss": 0.5297,
+      "step": 450
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.5227681994438171,
+      "eval_runtime": 394.7112,
+      "eval_samples_per_second": 5.457,
+      "eval_steps_per_second": 0.684,
+      "step": 450
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.1926855742931366,
+      "learning_rate": 2.074025148547635e-06,
+      "loss": 0.5114,
+      "step": 500
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 0.5151167511940002,
+      "eval_runtime": 390.7412,
+      "eval_samples_per_second": 5.513,
+      "eval_steps_per_second": 0.691,
+      "step": 500
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.20605137944221497,
+      "learning_rate": 1.7926354830241926e-06,
+      "loss": 0.5109,
+      "step": 550
+    },
+    {
+      "epoch": 1.05,
+      "eval_loss": 0.5088621973991394,
+      "eval_runtime": 392.8267,
+      "eval_samples_per_second": 5.483,
+      "eval_steps_per_second": 0.687,
+      "step": 550
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.23452071845531464,
+      "learning_rate": 1.5e-06,
+      "loss": 0.5079,
+      "step": 600
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.5038764476776123,
+      "eval_runtime": 391.3908,
+      "eval_samples_per_second": 5.503,
+      "eval_steps_per_second": 0.69,
+      "step": 600
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.22774113714694977,
+      "learning_rate": 1.2073645169758077e-06,
+      "loss": 0.4999,
+      "step": 650
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 0.5000301599502563,
+      "eval_runtime": 392.1009,
+      "eval_samples_per_second": 5.493,
+      "eval_steps_per_second": 0.689,
+      "step": 650
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.21539181470870972,
+      "learning_rate": 9.259748514523654e-07,
+      "loss": 0.4908,
+      "step": 700
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 0.4972001016139984,
+      "eval_runtime": 392.3879,
+      "eval_samples_per_second": 5.489,
+      "eval_steps_per_second": 0.688,
+      "step": 700
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.20129938423633575,
+      "learning_rate": 6.666446504705971e-07,
+      "loss": 0.4888,
+      "step": 750
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.4950333833694458,
+      "eval_runtime": 392.4542,
+      "eval_samples_per_second": 5.489,
+      "eval_steps_per_second": 0.688,
+      "step": 750
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.20948025584220886,
+      "learning_rate": 4.3933982822017883e-07,
+      "loss": 0.4915,
+      "step": 800
+    },
+    {
+      "epoch": 1.52,
+      "eval_loss": 0.49351951479911804,
+      "eval_runtime": 392.3544,
+      "eval_samples_per_second": 5.49,
+      "eval_steps_per_second": 0.688,
+      "step": 800
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.21380692720413208,
+      "learning_rate": 2.52795581546182e-07,
+      "loss": 0.4935,
+      "step": 850
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.4924446642398834,
+      "eval_runtime": 392.3544,
+      "eval_samples_per_second": 5.49,
+      "eval_steps_per_second": 0.688,
+      "step": 850
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.2027772217988968,
+      "learning_rate": 1.141807012330699e-07,
+      "loss": 0.4869,
+      "step": 900
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.4918237328529358,
+      "eval_runtime": 392.4738,
+      "eval_samples_per_second": 5.488,
+      "eval_steps_per_second": 0.688,
+      "step": 900
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.22568389773368835,
+      "learning_rate": 2.8822079395154353e-08,
+      "loss": 0.4887,
+      "step": 950
+    },
+    {
+      "epoch": 1.81,
+      "eval_loss": 0.4916115403175354,
+      "eval_runtime": 392.4881,
+      "eval_samples_per_second": 5.488,
+      "eval_steps_per_second": 0.688,
+      "step": 950
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.2142002135515213,
+      "learning_rate": 0.0,
+      "loss": 0.4898,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 0.4915645122528076,
+      "eval_runtime": 392.486,
+      "eval_samples_per_second": 5.488,
+      "eval_steps_per_second": 0.688,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "total_flos": 2.664713513598517e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a17bdb7672b38523cfec65be37a7754214e2c007a24a13ef228608dc9aaa4f
+size 4984