Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "k_proj",
+    "o_proj",
     "up_proj",
     "q_proj",
-    "o_proj",
     "down_proj",
-    "v_proj",
-    "k_proj"
+    "gate_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 sha256:056760f3ea5374461986f1028796cec251f177a9db6c479c5bc1d979411d89e6
+oid sha256:5ff9d95fcc09f2460d7be3e11cefcdde4395e784cd66d2c8beba02c60b763c90
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8155eaed1bf81a8d0c4e7fd4f6ef2c8341277b630d5dc56b26520a5e7fcfe746
+oid sha256:7ec1a8b3df8fc707962d6a4ce1716e207148ee591b39ad7bcb39f81f28ca0262
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638af6f593094a558f5283bf1669c955a044e33851610e2150ab691bd43844c0
+oid sha256:338de9bb6458aaded11e155b40b448a8adf8129f78f4768152c07a2e48b83e6a
 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": 0.0001532743227190865,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0019925661953481243,
+  "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": 0.0001532743227190865,
       "eval_loss": 1.3875150680541992,
-      "eval_runtime": 245.8851,
-      "eval_samples_per_second": 11.172,
-      "eval_steps_per_second": 5.588,
+      "eval_runtime": 246.9041,
+      "eval_samples_per_second": 11.126,
+      "eval_steps_per_second": 5.565,
       "step": 1
+    },
+    {
+      "epoch": 0.0007663716135954325,
+      "grad_norm": 0.35899266600608826,
+      "learning_rate": 5e-05,
+      "loss": 1.1895,
+      "step": 5
+    },
+    {
+      "epoch": 0.001532743227190865,
+      "grad_norm": 0.6321964859962463,
+      "learning_rate": 0.0001,
+      "loss": 1.1103,
+      "step": 10
+    },
+    {
+      "epoch": 0.001532743227190865,
+      "eval_loss": 1.3246690034866333,
+      "eval_runtime": 248.4262,
+      "eval_samples_per_second": 11.058,
+      "eval_steps_per_second": 5.531,
+      "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": 285028298784768.0,
+  "total_flos": 3664649555804160.0,
   "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:a4257f09e9962c35d45d511bfbfab9a4f10b5128b6fe8fcb0dd7bf95e19bd06b
+oid sha256:a1251e1e817aefbf064b2dbbe2288d206b1625193de66a40ce76fe809aae73f6
 size 6776