Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "o_proj",
-    "down_proj",
-    "q_proj",
     "gate_proj",
-    "k_proj"
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8d602b8c8217d2bad01c439cf265d8636e230eef9088012f7f0abb56d28cf2
+oid sha256:b0304deb94d880a7178e25c4a9e95080cad45ede8dec464157f33bd332f16447
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2191d72d7a4e92f1708c7172d5fb9681c38cdf111b4827525b1ec1097ccfd262
+oid sha256:a811aacff4dbcf4c4e10cb5d8bb1badbc2b48eebd1d3c4546998b6c6da9bb1cf
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a81cc94bb9784a99b66a3847a12e5edc941dafcbd050831d68c21b46d0ac7a
+oid sha256:2343ae5ff828c34e3305a42016ad344256fbf938ac207504145e5fbdf0daff67
 size 14244

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05405405405405406,
+  "epoch": 0.02702702702702703,
   "eval_steps": 3,
   "global_step": 10,
   "is_hyper_param_search": false,
@@ -9,105 +9,105 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.005405405405405406,
-      "grad_norm": 0.2000586837530136,
+      "epoch": 0.002702702702702703,
+      "grad_norm": 0.22516648471355438,
       "learning_rate": 2e-05,
-      "loss": 2.3204,
+      "loss": 2.4235,
       "step": 1
     },
     {
-      "epoch": 0.005405405405405406,
-      "eval_loss": 2.2008719444274902,
-      "eval_runtime": 9.7979,
-      "eval_samples_per_second": 7.961,
-      "eval_steps_per_second": 3.98,
+      "epoch": 0.002702702702702703,
+      "eval_loss": 2.200819492340088,
+      "eval_runtime": 8.0954,
+      "eval_samples_per_second": 9.635,
+      "eval_steps_per_second": 9.635,
       "step": 1
     },
     {
-      "epoch": 0.010810810810810811,
-      "grad_norm": 0.17591507732868195,
+      "epoch": 0.005405405405405406,
+      "grad_norm": 0.2626628577709198,
       "learning_rate": 4e-05,
-      "loss": 2.6394,
+      "loss": 2.2166,
       "step": 2
     },
     {
-      "epoch": 0.016216216216216217,
-      "grad_norm": 0.19049879908561707,
+      "epoch": 0.008108108108108109,
+      "grad_norm": 0.21446576714515686,
       "learning_rate": 6e-05,
-      "loss": 2.2241,
+      "loss": 2.6546,
       "step": 3
     },
     {
-      "epoch": 0.016216216216216217,
-      "eval_loss": 2.1992404460906982,
-      "eval_runtime": 9.8906,
-      "eval_samples_per_second": 7.886,
-      "eval_steps_per_second": 3.943,
+      "epoch": 0.008108108108108109,
+      "eval_loss": 2.199615955352783,
+      "eval_runtime": 8.2871,
+      "eval_samples_per_second": 9.412,
+      "eval_steps_per_second": 9.412,
       "step": 3
     },
     {
-      "epoch": 0.021621621621621623,
-      "grad_norm": 0.21317099034786224,
+      "epoch": 0.010810810810810811,
+      "grad_norm": 0.2510293424129486,
       "learning_rate": 8e-05,
-      "loss": 2.0634,
+      "loss": 2.6251,
       "step": 4
     },
     {
-      "epoch": 0.02702702702702703,
-      "grad_norm": 0.16591224074363708,
+      "epoch": 0.013513513513513514,
+      "grad_norm": 0.2600695788860321,
       "learning_rate": 0.0001,
-      "loss": 2.2234,
+      "loss": 2.0934,
       "step": 5
     },
     {
-      "epoch": 0.032432432432432434,
-      "grad_norm": 0.22719058394432068,
+      "epoch": 0.016216216216216217,
+      "grad_norm": 0.23503589630126953,
       "learning_rate": 0.00012,
-      "loss": 2.4093,
+      "loss": 2.3495,
       "step": 6
     },
     {
-      "epoch": 0.032432432432432434,
-      "eval_loss": 2.1915857791900635,
-      "eval_runtime": 9.9284,
-      "eval_samples_per_second": 7.856,
-      "eval_steps_per_second": 3.928,
+      "epoch": 0.016216216216216217,
+      "eval_loss": 2.193514585494995,
+      "eval_runtime": 8.4696,
+      "eval_samples_per_second": 9.209,
+      "eval_steps_per_second": 9.209,
       "step": 6
     },
     {
-      "epoch": 0.03783783783783784,
-      "grad_norm": 0.24013416469097137,
+      "epoch": 0.01891891891891892,
+      "grad_norm": 0.23834799230098724,
       "learning_rate": 0.00014,
-      "loss": 2.034,
+      "loss": 2.0365,
       "step": 7
     },
     {
-      "epoch": 0.043243243243243246,
-      "grad_norm": 0.19061008095741272,
+      "epoch": 0.021621621621621623,
+      "grad_norm": 0.34777796268463135,
       "learning_rate": 0.00016,
-      "loss": 2.0807,
+      "loss": 2.0777,
       "step": 8
     },
     {
-      "epoch": 0.04864864864864865,
-      "grad_norm": 0.22366337478160858,
+      "epoch": 0.024324324324324326,
+      "grad_norm": 0.2863074839115143,
       "learning_rate": 0.00018,
-      "loss": 2.2467,
+      "loss": 2.3295,
       "step": 9
     },
     {
-      "epoch": 0.04864864864864865,
-      "eval_loss": 2.179177761077881,
-      "eval_runtime": 9.9529,
-      "eval_samples_per_second": 7.837,
-      "eval_steps_per_second": 3.918,
+      "epoch": 0.024324324324324326,
+      "eval_loss": 2.1840600967407227,
+      "eval_runtime": 8.339,
+      "eval_samples_per_second": 9.354,
+      "eval_steps_per_second": 9.354,
       "step": 9
     },
     {
-      "epoch": 0.05405405405405406,
-      "grad_norm": 0.2424449622631073,
+      "epoch": 0.02702702702702703,
+      "grad_norm": 0.25496789813041687,
       "learning_rate": 0.0002,
-      "loss": 1.9704,
+      "loss": 2.1022,
       "step": 10
     }
   ],
@@ -128,7 +128,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6658431393988608.0,
+  "total_flos": 3467932965273600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46bccd6964f4291101ddc4731a06bfcf4544fcbb608a5a0128bc2068c8364f7b
+oid sha256:d5b80978b6cdcc9339ecc7931db757328a1ca9deca5507d6af70e88c187855a9
 size 6776