Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "qkv_proj",
-    "o_proj",
-    "gate_up_proj"
+    "gate_up_proj",
+    "down_proj",
+    "o_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:f13d0c712b984d3591cdda42d5779d25a1c2b32bd43b48520314d2d5658028fa
+oid sha256:e358913b62184ba3142216e265d2a3582465d95a35e1e18c1e3474c5121f167a
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a6f8607b0bd26bd14b93e5153dbba5c6419f5f02eab541a39c56286f69bb420
+oid sha256:78143e170decc0978c9cff279903e23c5b7e8ae81e0dd6c8a6dfbd30c98418ff
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c74673ff0bc06cd0ebb7731d803776a08382f09fba4601b17e24ff25336eaa
+oid sha256:f2a3d0f18704952f5e489fd373140093b1ec2232d5123df9941b8b0ec34244b4
 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": 3.3898592360952214e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00044068170069237874,
+  "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": 3.3898592360952214e-05,
       "eval_loss": 1.4055248498916626,
-      "eval_runtime": 2117.9858,
-      "eval_samples_per_second": 5.865,
-      "eval_steps_per_second": 2.933,
+      "eval_runtime": 2116.9701,
+      "eval_samples_per_second": 5.867,
+      "eval_steps_per_second": 2.934,
       "step": 1
+    },
+    {
+      "epoch": 0.00016949296180476106,
+      "grad_norm": 0.9714363217353821,
+      "learning_rate": 5e-05,
+      "loss": 5.1029,
+      "step": 5
+    },
+    {
+      "epoch": 0.0003389859236095221,
+      "grad_norm": 1.5137470960617065,
+      "learning_rate": 0.0001,
+      "loss": 5.8752,
+      "step": 10
+    },
+    {
+      "epoch": 0.0003389859236095221,
+      "eval_loss": 1.3639026880264282,
+      "eval_runtime": 2150.4467,
+      "eval_samples_per_second": 5.776,
+      "eval_steps_per_second": 2.888,
+      "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": 339736736563200.0,
+  "total_flos": 4416577575321600.0,
   "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 sha256:7bf925250b3b887b7a4a5f7621e3807c942cad64e420b75cbb662b327c8a3a6a
+oid sha256:b3d6e00d834399b2caa804735137dcd81dccdc7b3a02f224079d726a756d7d9b
 size 6776