Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
-    "v_proj",
     "k_proj",
-    "up_proj",
+    "v_proj",
+    "o_proj",
     "down_proj",
-    "gate_proj"
+    "gate_proj",
+    "up_proj",
+    "q_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:c5ff625acb830392c2976e370587f0ca62e802e16af5b58a89980f150dad1c19
+oid sha256:1b993db9391e28f36d11ff98ddc72b3055a937ffa17e400e697cf90c3b6c3704
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:479f7d1f0971f0f30afe9e5371bfa88e2271d4ec136d4a88fd2badc56837c3e0
+oid sha256:874bb28c0306c2c089e2049b02bd3602497f5f5866e17ceb5e41700c125ea200
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:18ede02b0d96dc677de5743502a84c45dd26a8f552c0b414b71c13f40e9c102e
 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": 6.501633535425775e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0008452123596053508,
+  "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": 6.501633535425775e-05,
       "eval_loss": 2.350724220275879,
-      "eval_runtime": 493.9058,
-      "eval_samples_per_second": 13.114,
-      "eval_steps_per_second": 6.558,
+      "eval_runtime": 495.2406,
+      "eval_samples_per_second": 13.078,
+      "eval_steps_per_second": 6.54,
       "step": 1
+    },
+    {
+      "epoch": 0.00032508167677128876,
+      "grad_norm": 21.5816707611084,
+      "learning_rate": 5e-05,
+      "loss": 8.7887,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006501633535425775,
+      "grad_norm": 21.14899444580078,
+      "learning_rate": 0.0001,
+      "loss": 9.016,
+      "step": 10
+    },
+    {
+      "epoch": 0.0006501633535425775,
+      "eval_loss": 2.096869468688965,
+      "eval_runtime": 496.257,
+      "eval_samples_per_second": 13.052,
+      "eval_steps_per_second": 6.527,
+      "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": 2672824493801472.0,
   "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 sha256:2f74203371245ba1ecdf6aa03ced7cbdbe1285f640efc58a2748002e9885cf63
+oid sha256:901f735915bd3f0d6dc9a9ae0e08b97c3f2a2ab27405aa19e5a49b72bdaaa0a5
 size 6776