Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "o_proj",
     "down_proj",
+    "k_proj",
+    "q_proj",
     "v_proj",
-    "o_proj",
     "up_proj",
-    "k_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:b2635eb34ad97d435f9df13302afd9e9cbdc80909c5d31f7d170af8243d0ac0b
+oid sha256:d7ea43b210c0b2d10608d716d873a5094ff60ea3b6245781d706102de80310b3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546ac45ec4eba1f35ca4aa01a7299888e3478b338e13d3c57bf8281c7ca70b99
+oid sha256:c0aadd28ce6d17d8f6a3ef12ff2b246e47d8ba044b98b9ddd2fc4b83da38900f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 0.0001362815576982045,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0017716602500766584,
+  "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": 0.0001362815576982045,
       "eval_loss": 3.762300968170166,
-      "eval_runtime": 357.6772,
+      "eval_runtime": 357.6618,
       "eval_samples_per_second": 8.639,
       "eval_steps_per_second": 4.32,
       "step": 1
+    },
+    {
+      "epoch": 0.0006814077884910225,
+      "grad_norm": 19.308378219604492,
+      "learning_rate": 5e-05,
+      "loss": 15.076,
+      "step": 5
+    },
+    {
+      "epoch": 0.001362815576982045,
+      "grad_norm": 9.135622024536133,
+      "learning_rate": 0.0001,
+      "loss": 13.6618,
+      "step": 10
+    },
+    {
+      "epoch": 0.001362815576982045,
+      "eval_loss": 3.3052594661712646,
+      "eval_runtime": 358.4211,
+      "eval_samples_per_second": 8.621,
+      "eval_steps_per_second": 4.311,
+      "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": 350688576012288.0,
+  "total_flos": 4558951488159744.0,
   "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:b3d9f2b77e5e65b769aebb3c1a906d7493b02486d19b0ccb3dd9d9e1c9a89bae
+oid sha256:ce1a8b2444d78cdb181440fdc4058816ae9ca922275d556c6ca2f50e46d83cda
 size 6776