Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "k_proj",
+    "q_proj",
     "up_proj",
     "gate_proj",
     "v_proj",
-    "q_proj",
-    "k_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce4e18302be44201fc7c82e3e155acb54431e7f618228855bd74b419f25c01c3
+oid sha256:5b32cc474bd19416b20dc9e4958e4bd1df993903b86c746f8b4bdec04768f075
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78438a09cdcfa65c5a077adf7d009c020dd44484b46bfab601d069843e2f47e7
+oid sha256:6f021aa4c2f925788dc65323d016c4d8b16c0b364507ff1f2ef80bee29b24da5
 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": 0.0042417815482502655,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.05514316012725345,
+  "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": 0.0042417815482502655,
       "eval_loss": 2.8640244007110596,
-      "eval_runtime": 8.7847,
-      "eval_samples_per_second": 11.383,
-      "eval_steps_per_second": 5.692,
+      "eval_runtime": 8.8089,
+      "eval_samples_per_second": 11.352,
+      "eval_steps_per_second": 5.676,
       "step": 1
+    },
+    {
+      "epoch": 0.021208907741251327,
+      "grad_norm": 23.904552459716797,
+      "learning_rate": 5e-05,
+      "loss": 12.3989,
+      "step": 5
+    },
+    {
+      "epoch": 0.042417815482502653,
+      "grad_norm": 24.06581687927246,
+      "learning_rate": 0.0001,
+      "loss": 7.864,
+      "step": 10
+    },
+    {
+      "epoch": 0.042417815482502653,
+      "eval_loss": 1.757564902305603,
+      "eval_runtime": 9.3206,
+      "eval_samples_per_second": 10.729,
+      "eval_steps_per_second": 5.364,
+      "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": 175266978594816.0,
+  "total_flos": 2322287466381312.0,
   "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:bde055005558503671d18ec15619b1356e641e670cf03bf84f2b95153a6eb892
+oid sha256:1abf7a9bb56cf5ab203608ea94c8b3de56531db5a06274ff9e5fbdf84a1d0adf
 size 6776