Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
     "v_proj",
-    "q_proj",
     "k_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
     "o_proj",
     "up_proj"
   ],

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38473b4e544d716c7710f10d2a256a510772706e172d34efc6c6023faed8d194
+oid sha256:9cb60cfb6a4e3bc1518b920996bb48b00754ed1b17a5ca60daf58b81f3687167
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afacdece9ebc131573c6dba1592c448a00862db876f6d4c7fbe65ec9bacdfeed
+oid sha256:4087e87e5a083938c3ff189682e3694473f025bd1a4bf489a875a45055b975fe
 size 97487290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6cd39cdb37120f55361cd5e0069f61be89d255f23a8450b4d3163474d73427f
+oid sha256:91b24fc1ce0ebd43a5a2c02d4cd0e240082f722605ae31afde9e2954adcd4790
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011276075925577898,
+  "epoch": 0.0005638037962788949,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00018793459875963165,
-      "grad_norm": 0.41265636682510376,
+      "grad_norm": 0.40805867314338684,
       "learning_rate": 2e-05,
       "loss": 2.0097,
       "step": 1
@@ -18,61 +18,32 @@
     {
       "epoch": 0.00018793459875963165,
       "eval_loss": 2.225860595703125,
-      "eval_runtime": 59.1454,
-      "eval_samples_per_second": 18.953,
-      "eval_steps_per_second": 18.953,
+      "eval_runtime": 104.7616,
+      "eval_samples_per_second": 10.7,
+      "eval_steps_per_second": 10.7,
       "step": 1
     },
     {
       "epoch": 0.0003758691975192633,
-      "grad_norm": 0.34109458327293396,
+      "grad_norm": 0.3363264501094818,
       "learning_rate": 4e-05,
       "loss": 2.0424,
       "step": 2
     },
     {
       "epoch": 0.0005638037962788949,
-      "grad_norm": 0.4408990442752838,
+      "grad_norm": 0.4387308359146118,
       "learning_rate": 6e-05,
-      "loss": 2.2435,
+      "loss": 2.2437,
       "step": 3
     },
     {
       "epoch": 0.0005638037962788949,
-      "eval_loss": 2.2232234477996826,
-      "eval_runtime": 53.5686,
-      "eval_samples_per_second": 20.926,
-      "eval_steps_per_second": 20.926,
+      "eval_loss": 2.223356246948242,
+      "eval_runtime": 105.324,
+      "eval_samples_per_second": 10.643,
+      "eval_steps_per_second": 10.643,
       "step": 3
-    },
-    {
-      "epoch": 0.0007517383950385266,
-      "grad_norm": 0.3058125972747803,
-      "learning_rate": 8e-05,
-      "loss": 2.1183,
-      "step": 4
-    },
-    {
-      "epoch": 0.0009396729937981583,
-      "grad_norm": 0.44318097829818726,
-      "learning_rate": 0.0001,
-      "loss": 2.2092,
-      "step": 5
-    },
-    {
-      "epoch": 0.0011276075925577898,
-      "grad_norm": 0.3183535933494568,
-      "learning_rate": 0.00012,
-      "loss": 2.2227,
-      "step": 6
-    },
-    {
-      "epoch": 0.0011276075925577898,
-      "eval_loss": 2.2024617195129395,
-      "eval_runtime": 54.1467,
-      "eval_samples_per_second": 20.703,
-      "eval_steps_per_second": 20.703,
-      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -92,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 417433827409920.0,
+  "total_flos": 208716913704960.0,
   "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 sha256:66aba1548284fb45544c3c449ae78c0d06cde4d353a7cacc54939951423f8e9a
+oid sha256:acaeb28a4fb49aa88292474a6784853956ad77b62156abc6a5e8cbc29594a649
 size 6776