Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_proj",
     "v_proj",
-    "o_proj"
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_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:e33b9c4d5b8234cc5f2bcab386d301080621fe4aa628b2481451f9774ec21779
+oid sha256:2d8cec64eafbb22c0974f73eb0d5962a0774530795ad6a2c3685e16b8d134ff6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:689f85e95b656860e4f35fdae01fbf0e0ae2a5ddca7501fa6b17d0fb08d15985
+oid sha256:c492c15d7ae480de707a0b49ad6ba415aeee005673407eda84c2bf36d63f401e
 size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534ce4aa0bf19f942c8fdb2c560920336f7a9e3abdfd0a3e25924b6b64b9bd8f
+oid sha256:a07c92839efa811b620c484869915929ecc981ec3cd50f8cb461afad0c34ae65
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4605ae3988d236e50132a8c5a5710439e239440b8e0450b03c26c8c1f78817
+oid sha256:29e8361359bebe2c84d4b0f767be090685ea4cd259d00d2df373b665a6d98ad3
 size 14512

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024324324324324326,
+  "epoch": 0.04864864864864865,
   "eval_steps": 3,
   "global_step": 9,
   "is_hyper_param_search": false,
@@ -9,98 +9,98 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.002702702702702703,
-      "grad_norm": 0.22516648471355438,
+      "epoch": 0.005405405405405406,
+      "grad_norm": 0.2000586837530136,
       "learning_rate": 2e-05,
-      "loss": 2.4235,
+      "loss": 2.3204,
       "step": 1
     },
     {
-      "epoch": 0.002702702702702703,
-      "eval_loss": 2.200819492340088,
-      "eval_runtime": 8.0954,
-      "eval_samples_per_second": 9.635,
-      "eval_steps_per_second": 9.635,
+      "epoch": 0.005405405405405406,
+      "eval_loss": 2.2008719444274902,
+      "eval_runtime": 9.7979,
+      "eval_samples_per_second": 7.961,
+      "eval_steps_per_second": 3.98,
       "step": 1
     },
     {
-      "epoch": 0.005405405405405406,
-      "grad_norm": 0.2626628577709198,
+      "epoch": 0.010810810810810811,
+      "grad_norm": 0.17591507732868195,
       "learning_rate": 4e-05,
-      "loss": 2.2166,
+      "loss": 2.6394,
       "step": 2
     },
     {
-      "epoch": 0.008108108108108109,
-      "grad_norm": 0.21446576714515686,
+      "epoch": 0.016216216216216217,
+      "grad_norm": 0.19049879908561707,
       "learning_rate": 6e-05,
-      "loss": 2.6546,
+      "loss": 2.2241,
       "step": 3
     },
     {
-      "epoch": 0.008108108108108109,
-      "eval_loss": 2.199615955352783,
-      "eval_runtime": 8.2871,
-      "eval_samples_per_second": 9.412,
-      "eval_steps_per_second": 9.412,
+      "epoch": 0.016216216216216217,
+      "eval_loss": 2.1992404460906982,
+      "eval_runtime": 9.8906,
+      "eval_samples_per_second": 7.886,
+      "eval_steps_per_second": 3.943,
       "step": 3
     },
     {
-      "epoch": 0.010810810810810811,
-      "grad_norm": 0.2510293424129486,
+      "epoch": 0.021621621621621623,
+      "grad_norm": 0.21317099034786224,
       "learning_rate": 8e-05,
-      "loss": 2.6251,
+      "loss": 2.0634,
       "step": 4
     },
     {
-      "epoch": 0.013513513513513514,
-      "grad_norm": 0.2600695788860321,
+      "epoch": 0.02702702702702703,
+      "grad_norm": 0.16591224074363708,
       "learning_rate": 0.0001,
-      "loss": 2.0934,
+      "loss": 2.2234,
       "step": 5
     },
     {
-      "epoch": 0.016216216216216217,
-      "grad_norm": 0.23503589630126953,
+      "epoch": 0.032432432432432434,
+      "grad_norm": 0.22719058394432068,
       "learning_rate": 0.00012,
-      "loss": 2.3495,
+      "loss": 2.4093,
       "step": 6
     },
     {
-      "epoch": 0.016216216216216217,
-      "eval_loss": 2.193514585494995,
-      "eval_runtime": 8.4696,
-      "eval_samples_per_second": 9.209,
-      "eval_steps_per_second": 9.209,
+      "epoch": 0.032432432432432434,
+      "eval_loss": 2.1915857791900635,
+      "eval_runtime": 9.9284,
+      "eval_samples_per_second": 7.856,
+      "eval_steps_per_second": 3.928,
       "step": 6
     },
     {
-      "epoch": 0.01891891891891892,
-      "grad_norm": 0.23834799230098724,
+      "epoch": 0.03783783783783784,
+      "grad_norm": 0.24013416469097137,
       "learning_rate": 0.00014,
-      "loss": 2.0365,
+      "loss": 2.034,
       "step": 7
     },
     {
-      "epoch": 0.021621621621621623,
-      "grad_norm": 0.34777796268463135,
+      "epoch": 0.043243243243243246,
+      "grad_norm": 0.19061008095741272,
       "learning_rate": 0.00016,
-      "loss": 2.0777,
+      "loss": 2.0807,
       "step": 8
     },
     {
-      "epoch": 0.024324324324324326,
-      "grad_norm": 0.2863074839115143,
+      "epoch": 0.04864864864864865,
+      "grad_norm": 0.22366337478160858,
       "learning_rate": 0.00018,
-      "loss": 2.3295,
+      "loss": 2.2467,
       "step": 9
     },
     {
-      "epoch": 0.024324324324324326,
-      "eval_loss": 2.1840600967407227,
-      "eval_runtime": 8.339,
-      "eval_samples_per_second": 9.354,
-      "eval_steps_per_second": 9.354,
+      "epoch": 0.04864864864864865,
+      "eval_loss": 2.179177761077881,
+      "eval_runtime": 9.9529,
+      "eval_samples_per_second": 7.837,
+      "eval_steps_per_second": 3.918,
       "step": 9
     }
   ],
@@ -121,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3098020115644416.0,
+  "total_flos": 6057323004952576.0,
   "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:d5b80978b6cdcc9339ecc7931db757328a1ca9deca5507d6af70e88c187855a9
+oid sha256:46bccd6964f4291101ddc4731a06bfcf4544fcbb608a5a0128bc2068c8364f7b
 size 6776