Upload 12 files

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/MythoMax-L2-13B-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559b044c54ed93032e11baaef37a9da01cde6ddbe133280b2b36d572d865c60a
+size 209736952

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9146e42b0d2ea30cd18adf8c9581ed9d883b1d11b52c9da6d09827764426ed9b
+size 419525626

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0ab9ab2bbbb8e29c8d4480d03d42827d41c72b15acfa23864d42561c8875a6
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59a103009f3230e51c40288ef6a33247523fa398934878b1e22a81660cbade8
+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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 1.847577452659607,
+  "best_model_checkpoint": "./results/checkpoint-75",
+  "epoch": 17.307692307692307,
+  "eval_steps": 25,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0002,
+      "loss": 3.1163,
+      "step": 25
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 1.9737789630889893,
+      "eval_runtime": 52.5251,
+      "eval_samples_per_second": 3.732,
+      "eval_steps_per_second": 0.476,
+      "step": 25
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.0002,
+      "loss": 1.3716,
+      "step": 50
+    },
+    {
+      "epoch": 3.85,
+      "eval_loss": 1.9462579488754272,
+      "eval_runtime": 52.5325,
+      "eval_samples_per_second": 3.731,
+      "eval_steps_per_second": 0.476,
+      "step": 50
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 0.0002,
+      "loss": 0.9683,
+      "step": 75
+    },
+    {
+      "epoch": 5.77,
+      "eval_loss": 1.847577452659607,
+      "eval_runtime": 52.5148,
+      "eval_samples_per_second": 3.732,
+      "eval_steps_per_second": 0.476,
+      "step": 75
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 0.0002,
+      "loss": 0.6227,
+      "step": 100
+    },
+    {
+      "epoch": 7.69,
+      "eval_loss": 2.0622782707214355,
+      "eval_runtime": 52.5202,
+      "eval_samples_per_second": 3.732,
+      "eval_steps_per_second": 0.476,
+      "step": 100
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 0.0002,
+      "loss": 0.4304,
+      "step": 125
+    },
+    {
+      "epoch": 9.62,
+      "eval_loss": 1.9112542867660522,
+      "eval_runtime": 52.5203,
+      "eval_samples_per_second": 3.732,
+      "eval_steps_per_second": 0.476,
+      "step": 125
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 0.0002,
+      "loss": 0.4078,
+      "step": 150
+    },
+    {
+      "epoch": 11.54,
+      "eval_loss": 1.959428310394287,
+      "eval_runtime": 52.5144,
+      "eval_samples_per_second": 3.732,
+      "eval_steps_per_second": 0.476,
+      "step": 150
+    },
+    {
+      "epoch": 13.46,
+      "learning_rate": 0.0002,
+      "loss": 0.3799,
+      "step": 175
+    },
+    {
+      "epoch": 13.46,
+      "eval_loss": 1.995124340057373,
+      "eval_runtime": 52.5123,
+      "eval_samples_per_second": 3.732,
+      "eval_steps_per_second": 0.476,
+      "step": 175
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 0.0002,
+      "loss": 0.3407,
+      "step": 200
+    },
+    {
+      "epoch": 15.38,
+      "eval_loss": 1.968113899230957,
+      "eval_runtime": 52.5326,
+      "eval_samples_per_second": 3.731,
+      "eval_steps_per_second": 0.476,
+      "step": 200
+    },
+    {
+      "epoch": 17.31,
+      "learning_rate": 0.0002,
+      "loss": 0.3182,
+      "step": 225
+    },
+    {
+      "epoch": 17.31,
+      "eval_loss": 1.8992738723754883,
+      "eval_runtime": 52.5263,
+      "eval_samples_per_second": 3.731,
+      "eval_steps_per_second": 0.476,
+      "step": 225
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 24,
+  "save_steps": 25,
+  "total_flos": 42316991354880.0,
+  "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 sha256:5ad0feacd6bc9cdb953ca60efcaae4ebec4a5256551bae9ef9f6dc3b984725d1
+size 4664