Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
-    "down_proj",
-    "up_proj",
     "o_proj",
     "q_proj",
-    "k_proj",
+    "up_proj",
+    "down_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77675b13e2cd5f6ffe04d72710ebdfff2b51b49a8d6c63df7a5ac7781297e3f7
+oid sha256:a0abe36ba0b0ef976ead1dc7ff0a64fbfb6ce5cd5d1d88940f4f5d6cf014b1f0
 size 137714904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96cb6a62ef9d58414647013ba2a3f7a3ace5fdfef2f04dd681f400318174318e
+oid sha256:821d2ce339b19d97ea8628afe64a5d4514be9fc28ad41de38585a5369b8b5e09
 size 70674004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d1cf0267799c19674d04561724387ad27dba86a2d5da6a20fa861bb1a83185
+oid sha256:dd0f9037f48f7cf42040857e4a42197433a0487867c3ffe08f41429048719150
 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": 0.010526315789473684,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.1368421052631579,
+  "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": 0.010526315789473684,
       "eval_loss": NaN,
-      "eval_runtime": 5.63,
-      "eval_samples_per_second": 7.282,
-      "eval_steps_per_second": 3.73,
+      "eval_runtime": 5.6364,
+      "eval_samples_per_second": 7.274,
+      "eval_steps_per_second": 3.726,
       "step": 1
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": NaN,
+      "eval_runtime": 4.5816,
+      "eval_samples_per_second": 8.949,
+      "eval_steps_per_second": 4.584,
+      "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": 344699839709184.0,
+  "total_flos": 4481097916219392.0,
   "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:db7d4d9db2d025f2bc151165a9e79116009ee45053b7c49676f77e6545d31a5e
+oid sha256:b0b10eedf34421661e66834362bbfe35da0f89553109ce8f5ea20a592df34ff6
 size 6776