Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:834def9aa97be7829225bcb9f92f5df826b2f24a41384ad38d94992bc41e2762
+oid sha256:032d16fab49f4183e6d689d9c0b1180bddda430d4b28d1f36abd04da21904fe1
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd56049780a36e9d079a394cf7e799b3f79e4772d294d874d55dd20902875841
+oid sha256:f9283cc9489842ff46413b848c9de23e897f98e38f7f22311ec2e902309163e8
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165ffe955f1fff238d7fa55fc3e704ed1175348f65c16d2a2296ab05188c0b98
+oid sha256:8c242d7799ebc0f126d889d39b72b14220f7b417fa995ba8ee59962ee6c98d92
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011353959693443088,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.014760147601476014,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0011353959693443088,
       "eval_loss": 1.4296112060546875,
-      "eval_runtime": 21.2758,
-      "eval_samples_per_second": 17.438,
-      "eval_steps_per_second": 8.742,
+      "eval_runtime": 21.5487,
+      "eval_samples_per_second": 17.217,
+      "eval_steps_per_second": 8.632,
       "step": 1
+    },
+    {
+      "epoch": 0.005676979846721544,
+      "grad_norm": 0.3469405174255371,
+      "learning_rate": 5e-05,
+      "loss": 1.3687,
+      "step": 5
+    },
+    {
+      "epoch": 0.011353959693443088,
+      "grad_norm": 0.46661630272865295,
+      "learning_rate": 0.0001,
+      "loss": 1.4407,
+      "step": 10
+    },
+    {
+      "epoch": 0.011353959693443088,
+      "eval_loss": 1.3932585716247559,
+      "eval_runtime": 19.9348,
+      "eval_samples_per_second": 18.611,
+      "eval_steps_per_second": 9.33,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 68560663609344.0,
+  "total_flos": 1011269788237824.0,
   "train_batch_size": 2,
   "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:ecc0faaf66ce11399528c37fb96c177b89f9f16a31afa5c549b38b89387a9fce
+oid sha256:0f1fd504c2014f1626f305c7a00a99f50fb5fb4caca9b905da532a6eb4eea71b
 size 6776