Upload folder using huggingface_hub

adapter_config.json

@@ -15,19 +15,19 @@
   "loftq_config": {},
   "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_up_proj",
+    "qkv_proj",
     "down_proj",
-    "qkv_proj"
+    "gate_up_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22840d7e8dcae71d4476dd0a66e0ca31b575990e7bac2c8eff79813f16256fec
-size 369133600
+oid sha256:94c0bd52d1b3d5f5eb6b16b50d1c8f91d34cdea75c302d56418b986080f10d87
+size 184584072

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c02c68dfbcdb61084dd7f46db8e6e75221857bbf1f38a42b2b6b5d87933e2c
+size 94020308

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2386fe9b5ee1c3b7f79ed97ed16698b48129c23c0e8968c678f21a7b93ff37a3
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17408c29434f7e5ce167b37e6963dcb7dc49c20e004c4b05cb0acf9ec056e6b
+size 1064

trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4763860369609856,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08213552361396304,
+      "grad_norm": 2.6946747303009033,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 2.9625,
+      "step": 5
+    },
+    {
+      "epoch": 0.16427104722792607,
+      "grad_norm": 2.452622890472412,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 2.667,
+      "step": 10
+    },
+    {
+      "epoch": 0.2464065708418891,
+      "grad_norm": 1.838152527809143,
+      "learning_rate": 9.980973490458728e-05,
+      "loss": 2.6454,
+      "step": 15
+    },
+    {
+      "epoch": 0.32854209445585214,
+      "grad_norm": 1.3952709436416626,
+      "learning_rate": 9.865224352899119e-05,
+      "loss": 2.4943,
+      "step": 20
+    },
+    {
+      "epoch": 0.4106776180698152,
+      "grad_norm": 1.686697006225586,
+      "learning_rate": 9.646737621134112e-05,
+      "loss": 2.567,
+      "step": 25
+    },
+    {
+      "epoch": 0.4928131416837782,
+      "grad_norm": 1.4075995683670044,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 2.3825,
+      "step": 30
+    },
+    {
+      "epoch": 0.5749486652977412,
+      "grad_norm": 1.6584903001785278,
+      "learning_rate": 8.922078324597879e-05,
+      "loss": 2.5749,
+      "step": 35
+    },
+    {
+      "epoch": 0.6570841889117043,
+      "grad_norm": 1.1556156873703003,
+      "learning_rate": 8.43120818934367e-05,
+      "loss": 2.402,
+      "step": 40
+    },
+    {
+      "epoch": 0.7392197125256673,
+      "grad_norm": 1.455573320388794,
+      "learning_rate": 7.86788218175523e-05,
+      "loss": 2.4118,
+      "step": 45
+    },
+    {
+      "epoch": 0.8213552361396304,
+      "grad_norm": 1.4337719678878784,
+      "learning_rate": 7.243995901002312e-05,
+      "loss": 2.3919,
+      "step": 50
+    },
+    {
+      "epoch": 0.9034907597535934,
+      "grad_norm": 1.5800418853759766,
+      "learning_rate": 6.572723780758069e-05,
+      "loss": 2.4384,
+      "step": 55
+    },
+    {
+      "epoch": 0.9856262833675564,
+      "grad_norm": 1.234969973564148,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.3536,
+      "step": 60
+    },
+    {
+      "epoch": 1.0657084188911705,
+      "grad_norm": 1.7878531217575073,
+      "learning_rate": 5.145423593715557e-05,
+      "loss": 2.1054,
+      "step": 65
+    },
+    {
+      "epoch": 1.1478439425051334,
+      "grad_norm": 1.651210069656372,
+      "learning_rate": 4.4195354293738484e-05,
+      "loss": 2.0509,
+      "step": 70
+    },
+    {
+      "epoch": 1.2299794661190966,
+      "grad_norm": 1.3757984638214111,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.0914,
+      "step": 75
+    },
+    {
+      "epoch": 1.3121149897330595,
+      "grad_norm": 1.2086457014083862,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 2.0147,
+      "step": 80
+    },
+    {
+      "epoch": 1.3942505133470227,
+      "grad_norm": 1.3752062320709229,
+      "learning_rate": 2.3751170983272e-05,
+      "loss": 2.0139,
+      "step": 85
+    },
+    {
+      "epoch": 1.4763860369609856,
+      "grad_norm": 1.567840814590454,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.9623,
+      "step": 90
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.249046274671821e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9d992b48539fa9fd94e419ca079a88a5d5955a44805fabc11b0801c053a28e
-size 5496
+oid sha256:ac77b392c05639c32d6a049505f4cd1831323ef1ceafcbc43faf53f380291318
+size 5560