Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "down_proj",
-    "k_proj",
     "gate_proj",
-    "q_proj",
-    "v_proj",
     "o_proj",
-    "up_proj"
+    "k_proj",
+    "q_proj",
+    "v_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 sha256:7aea8c61243773e961ea34f38ee180a47caeb55a95e41c3ce9910bc54852f457
+oid sha256:49c14d6efb6888f583f7d3e02e9a88f053d19caf979e17cecd6c17fcb66c5407
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c299b8b8f72f29e625eb55a61376c868ba82cc9bb7503f0c35d216eb10a49732
+oid sha256:24118ddef6fa6271e86fc9aef75261f97fc7e901ccdde6319c83dadc04ef3d99
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:43f0afd2a6da0fca19f600fb0b6d301534483f4096658807dd63f0bc368c2a3d
 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": 0.002008032128514056,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.02610441767068273,
+  "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": 0.002008032128514056,
       "eval_loss": 1.3564062118530273,
-      "eval_runtime": 15.1065,
-      "eval_samples_per_second": 13.901,
-      "eval_steps_per_second": 6.951,
+      "eval_runtime": 15.0793,
+      "eval_samples_per_second": 13.926,
+      "eval_steps_per_second": 6.963,
       "step": 1
+    },
+    {
+      "epoch": 0.010040160642570281,
+      "grad_norm": 0.5504012107849121,
+      "learning_rate": 5e-05,
+      "loss": 1.3271,
+      "step": 5
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "grad_norm": 0.6484191417694092,
+      "learning_rate": 0.0001,
+      "loss": 1.1678,
+      "step": 10
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "eval_loss": 1.2729361057281494,
+      "eval_runtime": 15.2427,
+      "eval_samples_per_second": 13.777,
+      "eval_steps_per_second": 6.889,
+      "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": 231195531018240.0,
+  "total_flos": 2913063690829824.0,
   "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 sha256:3fdb886c42278cabc759eabdb66dd73857096e18cb7c8501f773186d28a2968f
+oid sha256:ec409c34243746d33433498546778632fafe197cec40f4b26c58b3dda957bd17
 size 6776