Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
+    "o_proj",
     "down_proj",
     "q_proj",
+    "k_proj",
+    "v_proj",
     "gate_proj",
-    "o_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83130f393abacee5a764774e85a6a21ccd30e4b13897fe64f44af9f8a3397534
+oid sha256:dab56d4df0a16880ba70f97d626ec6c4bf40ce4e80efa22d3128de0e66a0092b
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a85252467a4b95c45de80afb2890eb41db6fe436ac22e22b49c1aa9c1d784c
+oid sha256:7bfaad8223a94bf1c5f5d099608c18efe7cd8e39115a40285cc98e75fcfa9723
 size 97487290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6cd39cdb37120f55361cd5e0069f61be89d255f23a8450b4d3163474d73427f
+oid sha256:011d57303a75fb8a2e485a8073e0f691c69b7d80a9f1120b703e475e9e6035b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011276075925577898,
+  "epoch": 0.001691411388836685,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00018793459875963165,
-      "grad_norm": 0.40805867314338684,
+      "grad_norm": 0.4121508002281189,
       "learning_rate": 2e-05,
       "loss": 2.0097,
       "step": 1
@@ -18,61 +18,90 @@
     {
       "epoch": 0.00018793459875963165,
       "eval_loss": 2.225860595703125,
-      "eval_runtime": 104.7616,
-      "eval_samples_per_second": 10.7,
-      "eval_steps_per_second": 10.7,
+      "eval_runtime": 104.6968,
+      "eval_samples_per_second": 10.707,
+      "eval_steps_per_second": 10.707,
       "step": 1
     },
     {
       "epoch": 0.0003758691975192633,
-      "grad_norm": 0.3363264501094818,
+      "grad_norm": 0.34095901250839233,
       "learning_rate": 4e-05,
       "loss": 2.0424,
       "step": 2
     },
     {
       "epoch": 0.0005638037962788949,
-      "grad_norm": 0.4387308359146118,
+      "grad_norm": 0.4388081431388855,
       "learning_rate": 6e-05,
-      "loss": 2.2437,
+      "loss": 2.2435,
       "step": 3
     },
     {
       "epoch": 0.0005638037962788949,
-      "eval_loss": 2.223356246948242,
-      "eval_runtime": 105.324,
-      "eval_samples_per_second": 10.643,
-      "eval_steps_per_second": 10.643,
+      "eval_loss": 2.2231271266937256,
+      "eval_runtime": 105.4847,
+      "eval_samples_per_second": 10.627,
+      "eval_steps_per_second": 10.627,
       "step": 3
     },
     {
       "epoch": 0.0007517383950385266,
-      "grad_norm": 0.30487483739852905,
+      "grad_norm": 0.3048204183578491,
       "learning_rate": 8e-05,
-      "loss": 2.1183,
+      "loss": 2.1182,
       "step": 4
     },
     {
       "epoch": 0.0009396729937981583,
-      "grad_norm": 0.44409823417663574,
+      "grad_norm": 0.4445512592792511,
       "learning_rate": 0.0001,
       "loss": 2.2092,
       "step": 5
     },
     {
       "epoch": 0.0011276075925577898,
-      "grad_norm": 0.31591424345970154,
+      "grad_norm": 0.3167805075645447,
       "learning_rate": 0.00012,
-      "loss": 2.223,
+      "loss": 2.2226,
       "step": 6
     },
     {
       "epoch": 0.0011276075925577898,
-      "eval_loss": 2.2032065391540527,
-      "eval_runtime": 104.9365,
-      "eval_samples_per_second": 10.683,
-      "eval_steps_per_second": 10.683,
+      "eval_loss": 2.202314615249634,
+      "eval_runtime": 104.9224,
+      "eval_samples_per_second": 10.684,
+      "eval_steps_per_second": 10.684,
       "step": 6
+    },
+    {
+      "epoch": 0.0013155421913174216,
+      "grad_norm": 0.49454212188720703,
+      "learning_rate": 0.00014,
+      "loss": 2.1979,
+      "step": 7
+    },
+    {
+      "epoch": 0.0015034767900770532,
+      "grad_norm": 0.387566477060318,
+      "learning_rate": 0.00016,
+      "loss": 2.1436,
+      "step": 8
+    },
+    {
+      "epoch": 0.001691411388836685,
+      "grad_norm": 0.36808285117149353,
+      "learning_rate": 0.00018,
+      "loss": 2.0588,
+      "step": 9
+    },
+    {
+      "epoch": 0.001691411388836685,
+      "eval_loss": 2.1498522758483887,
+      "eval_runtime": 104.9809,
+      "eval_samples_per_second": 10.678,
+      "eval_steps_per_second": 10.678,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 417433827409920.0,
+  "total_flos": 626150741114880.0,
   "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:acaeb28a4fb49aa88292474a6784853956ad77b62156abc6a5e8cbc29594a649
+oid sha256:abb88f4cc1adc89d4050bb1bb8aee4d5e2999228bec3f38fcda07d103361cace
 size 6776