Upload 3 files

training_log.json

@@ -0,0 +1,16 @@
+{
+  "base_model_name": "maywell_Synatra-10.7B-v0.4",
+  "base_model_class": "LlamaForCausalLM",
+  "base_loaded_in_4bit": true,
+  "base_loaded_in_8bit": false,
+  "projections": "q, v",
+  "loss": 1.5643,
+  "learning_rate": 8.935678962196381e-10,
+  "epoch": 2.99,
+  "current_steps": 7627,
+  "train_runtime": 47144.0886,
+  "train_samples_per_second": 2.6,
+  "train_steps_per_second": 0.01,
+  "total_flos": 1.991968191814828e+18,
+  "train_loss": 1.6426315012717896
+}

training_parameters.json

@@ -0,0 +1,37 @@
+{
+  "lora_name": "SAD",
+  "always_override": false,
+  "q_proj_en": true,
+  "v_proj_en": true,
+  "k_proj_en": false,
+  "o_proj_en": false,
+  "gate_proj_en": false,
+  "down_proj_en": false,
+  "up_proj_en": false,
+  "save_steps": 0.0,
+  "micro_batch_size": 16,
+  "batch_size": 256,
+  "epochs": 3.0,
+  "learning_rate": "2e-5",
+  "lr_scheduler_type": "cosine",
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "cutoff_len": 256,
+  "dataset": "None",
+  "eval_dataset": "None",
+  "format": "None",
+  "eval_steps": 100.0,
+  "raw_text_file": "saf",
+  "overlap_len": 128,
+  "newline_favor_len": 128,
+  "higher_rank_limit": false,
+  "warmup_steps": 100.0,
+  "optimizer": "adamw_torch",
+  "hard_cut_string": "\\n\\n",
+  "train_only_after": "",
+  "stop_at_loss": 0,
+  "add_eos_token": false,
+  "min_chars": 3.0,
+  "report_to": "tensorboard"
+}

training_prompt.json

@@ -0,0 +1,3 @@
+{
+  "template_type": "raw_text"
+}