Upload 9 files

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": true,
+  "use_rslora": false
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663c2e9b3a135feb89d74cdbd30a2a94171add10eac2d8b3bc633b0475b284f0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9cac68c495800a4bdcb66ffc3cc1e8f81886b9e59bf61baf66314bb15b9839
+size 1064

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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": 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": [],
+  "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": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6666666666666666,
+  "eval_steps": 50,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.8346723914146423,
+      "learning_rate": 0.000463751348237005,
+      "loss": 1.4282,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_loss": 1.2206487655639648,
+      "eval_runtime": 15.6057,
+      "eval_samples_per_second": 3.204,
+      "eval_steps_per_second": 0.449,
+      "step": 50
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.8318817019462585,
+      "learning_rate": 0.00034191042415818,
+      "loss": 1.1621,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 1.1499574184417725,
+      "eval_runtime": 15.583,
+      "eval_samples_per_second": 3.209,
+      "eval_steps_per_second": 0.449,
+      "step": 100
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4959808886051178,
+      "learning_rate": 0.00018268669172909137,
+      "loss": 1.0867,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.11073637008667,
+      "eval_runtime": 15.5841,
+      "eval_samples_per_second": 3.208,
+      "eval_steps_per_second": 0.449,
+      "step": 150
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.5760366916656494,
+      "learning_rate": 5.0841360885691e-05,
+      "loss": 1.0558,
+      "step": 200
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 1.0509577989578247,
+      "eval_runtime": 15.6001,
+      "eval_samples_per_second": 3.205,
+      "eval_steps_per_second": 0.449,
+      "step": 200
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5697112679481506,
+      "learning_rate": 0.0,
+      "loss": 1.0129,
+      "step": 250
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 1.0394231081008911,
+      "eval_runtime": 15.5661,
+      "eval_samples_per_second": 3.212,
+      "eval_steps_per_second": 0.45,
+      "step": 250
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "total_flos": 1.5178342352633856e+16,
+  "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:b5f40f0fe2374c35971bd6ceb3cb7f08cfe599f139dbbaaf3ba440b680f765cc
+size 4984