Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
     "o_proj",
-    "up_proj",
+    "down_proj",
     "k_proj",
+    "v_proj",
+    "q_proj",
     "gate_proj",
-    "q_proj"
+    "up_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 sha256:393bf5920395f21e6c5807c62f57a3718c1bb8553eebecd8b8b0efc2dbf83753
+oid sha256:10d19ccffba953434e3e9ae7e1e122cf2f928d5a7a77695bcf86435b6dc699df
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa73379984d1c03a9ad499bc9a69cda805d9e1edff0e10dbdf13f3382c567227
+oid sha256:bb463f5d6b9b75ecfff8c6ad91ac67109222ffb6d0e30748091efdb73ce2b535
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 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": 0.0008592910848549946,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01117078410311493,
+  "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": 0.0008592910848549946,
       "eval_loss": 2.4728493690490723,
-      "eval_runtime": 32.6258,
-      "eval_samples_per_second": 15.019,
-      "eval_steps_per_second": 7.509,
+      "eval_runtime": 32.4978,
+      "eval_samples_per_second": 15.078,
+      "eval_steps_per_second": 7.539,
       "step": 1
+    },
+    {
+      "epoch": 0.004296455424274973,
+      "grad_norm": 1.197363257408142,
+      "learning_rate": 5e-05,
+      "loss": 2.4877,
+      "step": 5
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "grad_norm": 1.2792778015136719,
+      "learning_rate": 0.0001,
+      "loss": 2.1751,
+      "step": 10
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "eval_loss": 2.1013641357421875,
+      "eval_runtime": 32.7282,
+      "eval_samples_per_second": 14.972,
+      "eval_steps_per_second": 7.486,
+      "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": 184956424814592.0,
+  "total_flos": 2404433522589696.0,
   "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:fe1af286d762e7d82ae71d9295ebadb0448a4e938ab0b28ba073a4f5914c53ca
+oid sha256:37f44f1d7d7a25444f22ca8843723e150ffa4bf425a91b69a0734043ca3695d5
 size 6776