Upload folder using huggingface_hub

adapter_config.json

@@ -10,20 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 256,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "qkv_proj",
     "gate_up_proj",
     "o_proj",
-    "down_proj",
-    "qkv_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a61de56fd524d496a06ffa8746819d8e60bcee582b012ae9c7732e69f55afb4
-size 805341552
+oid sha256:4ab943d089195aee5a7d89eb7cbf4f8bb6a29830bf9d5362cfc3fa4620050cd7
+size 100697728

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87a937c302089f213c4c8debfebde704cef39c592075c999f0bdb721a58c204
+size 201541754

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6722c0add00e4b206681879df404580407195f33d5032ab48ba0ba63e22eb03
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5cf7cb76fe4fe926cdcab05642e207fe9a3542a59dca1022a55729c3475a6a
+size 1064

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 87,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.32139214873313904,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 1.1359,
+      "step": 20
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.45712536573410034,
+      "learning_rate": 9.382716049382717e-05,
+      "loss": 0.9847,
+      "step": 40
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.40747180581092834,
+      "learning_rate": 6.91358024691358e-05,
+      "loss": 0.9306,
+      "step": 60
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.593609094619751,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.8252,
+      "step": 80
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1835707778883584e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9176a052da88a3f596cb9f84332e997d7950b292b7824c1a2d3f69688851f3
+oid sha256:9520806f662b981aab48fdfeb5b39944a9e24261fed20c3e6c035584238da225
 size 5432