Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
     "v_proj",
-    "k_proj",
+    "gate_proj",
     "q_proj",
-    "up_proj",
-    "gate_proj"
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "up_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 sha256:7029aea25531ea973d197ebd079ac88e1cce1fe252aa7ede66d168a592129b8c
+oid sha256:a43e0e965dc4259a92832122b11c67e2ffb649990829b841c8472a727a002ca5
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b7bd8267e04cd7e2d1d2563e1fe6c53f129fa1d2a7b5f1d6da3f36eff59a2e
+oid sha256:77565fb688e625a82712b1757a1187e13ad45dd76171a2b31fafe37eaf3d05d4
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f20e41f3077d86e7f18bdd164475600076f806010f903908839f21bd8a634a
+oid sha256:00fb6c6886659deb5bb37c3ff91f94b4bebef32a5b5659f8ccec56b94dc6d7a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006560065600656006,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.08528085280852808,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.006560065600656006,
       "eval_loss": NaN,
-      "eval_runtime": 23.3486,
-      "eval_samples_per_second": 43.985,
-      "eval_steps_per_second": 5.525,
+      "eval_runtime": 23.3316,
+      "eval_samples_per_second": 44.018,
+      "eval_steps_per_second": 5.529,
       "step": 1
+    },
+    {
+      "epoch": 0.06560065600656007,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.06560065600656007,
+      "eval_loss": NaN,
+      "eval_runtime": 22.0132,
+      "eval_samples_per_second": 46.654,
+      "eval_steps_per_second": 5.86,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 284922124173312.0,
+  "total_flos": 3703987614253056.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8cab05b16a4f63b23af72438edd02d0c97cbf0331d1f79938127de82cdecf1
+oid sha256:ce273a1c423e0bcd313d5770182f70f8871c93899b54a682b3a6a4d0cafd2441
 size 6776