Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44dc16f8539274a37ef7ebaf9c6094c4021150a6932d11bd1b7f758ad0db7414
+oid sha256:acac02bed7065833fc441f8a16002f811048037c52fdec67b59f4937dae36a4d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03be0eeaa02162c453122bcb316bfbcd1e245303a03fa9af864ad7018526c4b
+oid sha256:db8083f98b81d5d9ed291011647dc1759258a5710e214c13c3d7a038f31285e3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0525df66869b0adf8d756d9e95d76ef7874d6f8df8ffd52f14c9f432ae93afc8
+oid sha256:c682b407b21541d71a29dc7003999c781bae916db960904cb9bf02cf91709a8b
 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": 8.432396423820677e-06,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0001096211535096688,
+  "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": 8.432396423820677e-06,
       "eval_loss": 0.8909456729888916,
-      "eval_runtime": 4493.4081,
-      "eval_samples_per_second": 11.113,
-      "eval_steps_per_second": 5.556,
+      "eval_runtime": 4480.4241,
+      "eval_samples_per_second": 11.145,
+      "eval_steps_per_second": 5.572,
       "step": 1
+    },
+    {
+      "epoch": 4.216198211910338e-05,
+      "grad_norm": 4.769817352294922,
+      "learning_rate": 5e-05,
+      "loss": 3.4832,
+      "step": 5
+    },
+    {
+      "epoch": 8.432396423820676e-05,
+      "grad_norm": 4.518204212188721,
+      "learning_rate": 0.0001,
+      "loss": 3.555,
+      "step": 10
+    },
+    {
+      "epoch": 8.432396423820676e-05,
+      "eval_loss": 0.8294536471366882,
+      "eval_runtime": 4497.7777,
+      "eval_samples_per_second": 11.102,
+      "eval_steps_per_second": 5.551,
+      "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": 306852504010752.0,
+  "total_flos": 3463049688121344.0,
   "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:a6c9de51227fb8740fa5f0aebc7cdfef79b3363117e2953f42d9bca2fa2563c7
+oid sha256:555d2ca77d88aad82e0560eb333cbe2afbe2b94047f9addc0388114362ef0e83
 size 6776