Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "up_proj",
     "v_proj",
-    "k_proj",
-    "down_proj",
     "q_proj",
     "o_proj",
-    "gate_proj"
+    "gate_proj",
+    "k_proj",
+    "down_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 sha256:06d28abf777f221b9473069df0705c2049f50f6132aa9606af5150ae0013b6d3
+oid sha256:d3119e0c7daf728c00e6d59672457883fe65de31326575251b02ff3d264e68d5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce6d8c9a5a62433afca11ae099482b0ba980862e994a4614051a689ae12fdfa
+oid sha256:48fad25b264071fe8880f8ff33b6740c669b4a6bd5b1294b1a6ce1956b72ab6b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:ada9b88cecb69c9d2d8d4079789122084e4f2f601b6cf82350a60242621e3280
 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": 0.010230179028132993,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.1329923273657289,
+  "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": 0.010230179028132993,
       "eval_loss": 1.7183011770248413,
-      "eval_runtime": 2.8404,
-      "eval_samples_per_second": 14.787,
-      "eval_steps_per_second": 7.393,
+      "eval_runtime": 2.8418,
+      "eval_samples_per_second": 14.78,
+      "eval_steps_per_second": 7.39,
       "step": 1
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "grad_norm": 31.760643005371094,
+      "learning_rate": 5e-05,
+      "loss": 6.9221,
+      "step": 5
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "grad_norm": 24.04104995727539,
+      "learning_rate": 0.0001,
+      "loss": 5.6407,
+      "step": 10
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "eval_loss": 1.2962255477905273,
+      "eval_runtime": 2.8947,
+      "eval_samples_per_second": 14.509,
+      "eval_steps_per_second": 7.255,
+      "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": 175270199820288.0,
+  "total_flos": 2278512597663744.0,
   "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:dddd97598f78eaf17a3fe74cdacb28fa7f7d7c7c0b859f1d2035955f42b290b7
+oid sha256:ded20cfc84f542edb89150e6d5032f6309e630e6ccb3426c49d13822701db455
 size 6776