Upload 11 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": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e17b45366bbcc442552f7d3c7109ef1996c2bbd18fc117bf385448ad8bc0c3
+size 109069176

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8bc56cdd8903bd6f43f1bc9888b80a0b4c5dd14343505f48fea92cf20c2b5e
+size 218182458

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3a570609e09abdf429cfed01b0d34829ebc9b3bdfe5c8a428cbe573d1c06e3
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ffe17229f7cefebd5d2cacf3f2c29de3593f83db432b23b09feec31b623a01
+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 +1,171 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6666666666666666,
+  "eval_steps": 25,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.5077394843101501,
+      "learning_rate": 0.0004962796513310917,
+      "loss": 1.8786,
+      "step": 25
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "eval_loss": 1.2509196996688843,
+      "eval_runtime": 14.9139,
+      "eval_samples_per_second": 3.353,
+      "eval_steps_per_second": 0.469,
+      "step": 25
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.6929311752319336,
+      "learning_rate": 0.00047590709015212635,
+      "loss": 1.0271,
+      "step": 50
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "eval_loss": 1.2256547212600708,
+      "eval_runtime": 14.8976,
+      "eval_samples_per_second": 3.356,
+      "eval_steps_per_second": 0.47,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.5425320863723755,
+      "learning_rate": 0.0004391782039544238,
+      "loss": 1.3165,
+      "step": 75
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.1554468870162964,
+      "eval_runtime": 14.9773,
+      "eval_samples_per_second": 3.338,
+      "eval_steps_per_second": 0.467,
+      "step": 75
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.41945549845695496,
+      "learning_rate": 0.0003887522700533675,
+      "loss": 1.0036,
+      "step": 100
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "eval_loss": 1.1490750312805176,
+      "eval_runtime": 15.0033,
+      "eval_samples_per_second": 3.333,
+      "eval_steps_per_second": 0.467,
+      "step": 100
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.47675174474716187,
+      "learning_rate": 0.00032828027153100067,
+      "loss": 1.2587,
+      "step": 125
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_loss": 1.1076823472976685,
+      "eval_runtime": 14.9861,
+      "eval_samples_per_second": 3.336,
+      "eval_steps_per_second": 0.467,
+      "step": 125
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.39953848719596863,
+      "learning_rate": 0.0002621405555286121,
+      "loss": 0.9131,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.1073076725006104,
+      "eval_runtime": 14.9451,
+      "eval_samples_per_second": 3.346,
+      "eval_steps_per_second": 0.468,
+      "step": 150
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.42341387271881104,
+      "learning_rate": 0.00019512182828314883,
+      "loss": 1.1952,
+      "step": 175
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "eval_loss": 1.054356336593628,
+      "eval_runtime": 14.9684,
+      "eval_samples_per_second": 3.34,
+      "eval_steps_per_second": 0.468,
+      "step": 175
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.4625991582870483,
+      "learning_rate": 0.00013207643898130854,
+      "loss": 0.9034,
+      "step": 200
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 1.0499968528747559,
+      "eval_runtime": 15.0085,
+      "eval_samples_per_second": 3.331,
+      "eval_steps_per_second": 0.466,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.4041430354118347,
+      "learning_rate": 7.756905568047393e-05,
+      "loss": 1.1858,
+      "step": 225
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.0380258560180664,
+      "eval_runtime": 14.9267,
+      "eval_samples_per_second": 3.35,
+      "eval_steps_per_second": 0.469,
+      "step": 225
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.47007474303245544,
+      "learning_rate": 3.5546170173306444e-05,
+      "loss": 0.8296,
+      "step": 250
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 1.0288008451461792,
+      "eval_runtime": 14.9133,
+      "eval_samples_per_second": 3.353,
+      "eval_steps_per_second": 0.469,
+      "step": 250
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "total_flos": 1.5177993965223936e+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:b7da2d5845527bf67fcdc157a1775d9bc5ab5da58600ea733c4e50e28b677b13
+size 4920