Upload folder using huggingface_hub

adapter_config.json

@@ -30,13 +30,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "down_proj",
-    "gate_proj",
+    "k_proj",
     "v_proj",
     "q_proj",
     "o_proj",
-    "up_proj"
+    "up_proj",
+    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac49cdca2ce68d3a0d5f799978266d1eb979517c378a7ff8e123b937c8e5f12b
-size 335605144
+oid sha256:c2525c9e77856b784ce537ca8cdd1c322de2ebdc5198f25ebd5aae7681692176
+size 671149168

log_history.json

@@ -2,18 +2,18 @@
   "model": "mistralai/Mistral-7B-Instruct-v0.3",
   "seed": 1,
   "epochs_requested": 2,
-  "epoch_reached": 1.2835660580021482,
-  "global_step": 150,
-  "max_steps": 234,
+  "epoch_reached": 1.296983758700696,
+  "global_step": 140,
+  "max_steps": 216,
   "early_stopped": true,
-  "best_eval_loss": 2.0299525260925293,
-  "best_checkpoint": "finetuned_models/mistralai-Mistral-7B-Instruct-v0.3_seed1/checkpoint-120",
+  "best_eval_loss": 2.030566692352295,
+  "best_checkpoint": "finetuned_models/mistralai-Mistral-7B-Instruct-v0.3_seed1/checkpoint-110",
   "final_metrics": {
-    "eval_loss": 2.0299525260925293,
-    "eval_runtime": 11.3493,
-    "eval_samples_per_second": 40.884,
-    "eval_steps_per_second": 10.221,
-    "epoch": 1.2835660580021482
+    "eval_loss": 2.030566692352295,
+    "eval_runtime": 16.7007,
+    "eval_samples_per_second": 25.747,
+    "eval_steps_per_second": 6.467,
+    "epoch": 1.296983758700696
   },
   "learning_rate": 2.675263789416278e-05,
   "lora": {
@@ -31,183 +31,168 @@
   "early_stopping_patience": 3,
   "log_history": [
     {
-      "eval_loss": 2.148292303085327,
-      "eval_runtime": 10.6526,
-      "eval_samples_per_second": 43.557,
-      "eval_steps_per_second": 10.889,
-      "epoch": 0.08592910848549946,
+      "eval_loss": 2.141383647918701,
+      "eval_runtime": 11.0521,
+      "eval_samples_per_second": 38.907,
+      "eval_steps_per_second": 9.772,
+      "epoch": 0.09280742459396751,
       "step": 10
     },
     {
-      "eval_loss": 2.1104280948638916,
-      "eval_runtime": 10.6931,
-      "eval_samples_per_second": 43.392,
-      "eval_steps_per_second": 10.848,
-      "epoch": 0.17185821697099893,
+      "eval_loss": 2.103656053543091,
+      "eval_runtime": 10.789,
+      "eval_samples_per_second": 39.855,
+      "eval_steps_per_second": 10.01,
+      "epoch": 0.18561484918793503,
       "step": 20
     },
     {
-      "loss": 2.199215087890625,
-      "grad_norm": 1.9622942209243774,
-      "learning_rate": 2.64231507960414e-05,
-      "epoch": 0.21482277121374865,
+      "loss": 2.217321014404297,
+      "grad_norm": 1.7167869806289673,
+      "learning_rate": 2.6318280611836455e-05,
+      "epoch": 0.23201856148491878,
       "step": 25
     },
     {
-      "eval_loss": 2.0927581787109375,
-      "eval_runtime": 10.7138,
-      "eval_samples_per_second": 43.309,
-      "eval_steps_per_second": 10.827,
-      "epoch": 0.2577873254564984,
+      "eval_loss": 2.0854732990264893,
+      "eval_runtime": 10.8578,
+      "eval_samples_per_second": 39.603,
+      "eval_steps_per_second": 9.947,
+      "epoch": 0.27842227378190254,
       "step": 30
     },
     {
-      "eval_loss": 2.0791704654693604,
-      "eval_runtime": 10.7667,
-      "eval_samples_per_second": 43.096,
-      "eval_steps_per_second": 10.774,
-      "epoch": 0.34371643394199786,
+      "eval_loss": 2.0740013122558594,
+      "eval_runtime": 10.8703,
+      "eval_samples_per_second": 39.557,
+      "eval_steps_per_second": 9.935,
+      "epoch": 0.37122969837587005,
       "step": 40
     },
     {
-      "loss": 1.9954397583007812,
-      "grad_norm": 2.050276041030884,
-      "learning_rate": 2.4638324435570593e-05,
-      "epoch": 0.4296455424274973,
+      "loss": 1.9985250854492187,
+      "grad_norm": 2.1705639362335205,
+      "learning_rate": 2.4174302619519622e-05,
+      "epoch": 0.46403712296983757,
       "step": 50
     },
     {
-      "eval_loss": 2.069033622741699,
-      "eval_runtime": 10.6762,
-      "eval_samples_per_second": 43.461,
-      "eval_steps_per_second": 10.865,
-      "epoch": 0.4296455424274973,
+      "eval_loss": 2.0634052753448486,
+      "eval_runtime": 10.8606,
+      "eval_samples_per_second": 39.593,
+      "eval_steps_per_second": 9.944,
+      "epoch": 0.46403712296983757,
       "step": 50
     },
     {
-      "eval_loss": 2.0600428581237793,
-      "eval_runtime": 10.7639,
-      "eval_samples_per_second": 43.107,
-      "eval_steps_per_second": 10.777,
-      "epoch": 0.5155746509129968,
+      "eval_loss": 2.055530071258545,
+      "eval_runtime": 10.9203,
+      "eval_samples_per_second": 39.376,
+      "eval_steps_per_second": 9.89,
+      "epoch": 0.5568445475638051,
       "step": 60
     },
     {
-      "eval_loss": 2.05261492729187,
-      "eval_runtime": 10.8236,
-      "eval_samples_per_second": 42.869,
-      "eval_steps_per_second": 10.717,
-      "epoch": 0.6015037593984962,
+      "eval_loss": 2.0481231212615967,
+      "eval_runtime": 10.8423,
+      "eval_samples_per_second": 39.66,
+      "eval_steps_per_second": 9.961,
+      "epoch": 0.6496519721577726,
       "step": 70
     },
     {
-      "loss": 2.01874755859375,
-      "grad_norm": 1.6275213956832886,
-      "learning_rate": 2.150700736555706e-05,
-      "epoch": 0.644468313641246,
+      "loss": 2.014737548828125,
+      "grad_norm": 1.7425487041473389,
+      "learning_rate": 2.0523325458099818e-05,
+      "epoch": 0.6960556844547564,
       "step": 75
     },
     {
-      "eval_loss": 2.045529365539551,
-      "eval_runtime": 10.9449,
-      "eval_samples_per_second": 42.394,
-      "eval_steps_per_second": 10.599,
-      "epoch": 0.6874328678839957,
+      "eval_loss": 2.0430397987365723,
+      "eval_runtime": 11.0654,
+      "eval_samples_per_second": 38.86,
+      "eval_steps_per_second": 9.76,
+      "epoch": 0.7424593967517401,
       "step": 80
     },
     {
-      "eval_loss": 2.040515422821045,
-      "eval_runtime": 10.8044,
-      "eval_samples_per_second": 42.945,
-      "eval_steps_per_second": 10.736,
-      "epoch": 0.7733619763694952,
+      "eval_loss": 2.037876605987549,
+      "eval_runtime": 10.7984,
+      "eval_samples_per_second": 39.821,
+      "eval_steps_per_second": 10.001,
+      "epoch": 0.8352668213457076,
       "step": 90
     },
     {
-      "loss": 2.030762176513672,
-      "grad_norm": 1.8258167505264282,
-      "learning_rate": 1.7403581337786956e-05,
-      "epoch": 0.8592910848549946,
+      "loss": 1.9247970581054688,
+      "grad_norm": 2.195621967315674,
+      "learning_rate": 1.587489051192989e-05,
+      "epoch": 0.9280742459396751,
       "step": 100
     },
     {
-      "eval_loss": 2.0372297763824463,
-      "eval_runtime": 10.8682,
-      "eval_samples_per_second": 42.693,
-      "eval_steps_per_second": 10.673,
-      "epoch": 0.8592910848549946,
+      "eval_loss": 2.0337796211242676,
+      "eval_runtime": 10.9498,
+      "eval_samples_per_second": 39.27,
+      "eval_steps_per_second": 9.863,
+      "epoch": 0.9280742459396751,
       "step": 100
     },
     {
-      "eval_loss": 2.032543420791626,
-      "eval_runtime": 10.849,
-      "eval_samples_per_second": 42.769,
-      "eval_steps_per_second": 10.692,
-      "epoch": 0.9452201933404941,
+      "eval_loss": 2.030566692352295,
+      "eval_runtime": 10.9028,
+      "eval_samples_per_second": 39.439,
+      "eval_steps_per_second": 9.906,
+      "epoch": 1.0185614849187936,
       "step": 110
     },
     {
-      "eval_loss": 2.0299525260925293,
-      "eval_runtime": 10.7877,
-      "eval_samples_per_second": 43.012,
-      "eval_steps_per_second": 10.753,
-      "epoch": 1.0257787325456498,
+      "eval_loss": 2.0365731716156006,
+      "eval_runtime": 11.0196,
+      "eval_samples_per_second": 39.021,
+      "eval_steps_per_second": 9.801,
+      "epoch": 1.111368909512761,
       "step": 120
     },
     {
-      "loss": 1.8672723388671875,
-      "grad_norm": 1.8065060377120972,
-      "learning_rate": 1.2818653911396654e-05,
-      "epoch": 1.0687432867883995,
+      "loss": 1.867428741455078,
+      "grad_norm": 1.9571967124938965,
+      "learning_rate": 1.0877747382232885e-05,
+      "epoch": 1.1577726218097448,
       "step": 125
     },
     {
-      "eval_loss": 2.0359320640563965,
-      "eval_runtime": 10.7869,
-      "eval_samples_per_second": 43.015,
-      "eval_steps_per_second": 10.754,
-      "epoch": 1.1117078410311494,
+      "eval_loss": 2.041104793548584,
+      "eval_runtime": 10.9251,
+      "eval_samples_per_second": 39.359,
+      "eval_steps_per_second": 9.885,
+      "epoch": 1.2041763341067284,
       "step": 130
     },
     {
-      "eval_loss": 2.0388731956481934,
-      "eval_runtime": 10.7873,
-      "eval_samples_per_second": 43.014,
-      "eval_steps_per_second": 10.753,
-      "epoch": 1.1976369495166488,
+      "eval_loss": 2.038154363632202,
+      "eval_runtime": 11.0005,
+      "eval_samples_per_second": 39.089,
+      "eval_steps_per_second": 9.818,
+      "epoch": 1.296983758700696,
       "step": 140
     },
     {
-      "loss": 1.7887583923339845,
-      "grad_norm": 1.8141305446624756,
-      "learning_rate": 8.30040118076581e-06,
-      "epoch": 1.2835660580021482,
-      "step": 150
-    },
-    {
-      "eval_loss": 2.035823345184326,
-      "eval_runtime": 10.8244,
-      "eval_samples_per_second": 42.866,
-      "eval_steps_per_second": 10.716,
-      "epoch": 1.2835660580021482,
-      "step": 150
-    },
-    {
-      "train_runtime": 630.4929,
-      "train_samples_per_second": 11.81,
-      "train_steps_per_second": 0.371,
-      "total_flos": 7.985526070889677e+16,
-      "train_loss": 1.9833658854166667,
-      "epoch": 1.2835660580021482,
-      "step": 150
+      "train_runtime": 488.5924,
+      "train_samples_per_second": 14.106,
+      "train_steps_per_second": 0.442,
+      "total_flos": 7.636717925511987e+16,
+      "train_loss": 1.9583442006792342,
+      "epoch": 1.296983758700696,
+      "step": 140
     },
     {
-      "eval_loss": 2.0299525260925293,
-      "eval_runtime": 11.3493,
-      "eval_samples_per_second": 40.884,
-      "eval_steps_per_second": 10.221,
-      "epoch": 1.2835660580021482,
-      "step": 150
+      "eval_loss": 2.030566692352295,
+      "eval_runtime": 16.7007,
+      "eval_samples_per_second": 25.747,
+      "eval_steps_per_second": 6.467,
+      "epoch": 1.296983758700696,
+      "step": 140
     }
   ]
 }