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",
-    "k_proj",
     "gate_proj",
+    "o_proj",
     "q_proj",
+    "v_proj",
     "up_proj",
-    "v_proj"
+    "down_proj",
+    "k_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 sha256:1fcf2dac08c891caade5b869191f1d8e964148704e0483f173e8cda33c8bfb2b
+oid sha256:f577fc4335623be94ac3cbb9c1ad867e90540e5fc95d7d55bb92ca62f0797648
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f990d45edb32d960672774b80378e222a1f1580ccca19298a1319181fcc2e2a7
+oid sha256:68c514016b0b0b9a39bbe61ecce5671f6f1b863a7341d524b389c2c1319052a1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:2b8d3b0cd38ff8c140a46f8cd6b0fb2611ad2c4ebd59d9733c17b98b72f21091
 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": 0.0018034265103697023,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.023444544634806132,
+  "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": 0.0018034265103697023,
       "eval_loss": 1.5323797464370728,
-      "eval_runtime": 15.0465,
-      "eval_samples_per_second": 15.552,
-      "eval_steps_per_second": 7.776,
+      "eval_runtime": 15.1257,
+      "eval_samples_per_second": 15.47,
+      "eval_steps_per_second": 7.735,
       "step": 1
+    },
+    {
+      "epoch": 0.009017132551848512,
+      "grad_norm": 8.786983489990234,
+      "learning_rate": 5e-05,
+      "loss": 6.1675,
+      "step": 5
+    },
+    {
+      "epoch": 0.018034265103697024,
+      "grad_norm": 7.997146129608154,
+      "learning_rate": 0.0001,
+      "loss": 5.5276,
+      "step": 10
+    },
+    {
+      "epoch": 0.018034265103697024,
+      "eval_loss": 1.2454485893249512,
+      "eval_runtime": 15.4977,
+      "eval_samples_per_second": 15.099,
+      "eval_steps_per_second": 7.55,
+      "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": 175267179921408.0,
+  "total_flos": 2322290133958656.0,
   "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:c247c30386aa3ed8d46f1e3abba960067a5e43bf14bf4f43c0c9b40270ed93f8
+oid sha256:dcf09275280af842592f13d377006adbd735e3179d35b0feb59dcfa7c19c1f6f
 size 6776