Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "q_proj",
+    "o_proj",
     "v_proj",
+    "up_proj",
     "k_proj",
     "down_proj",
-    "o_proj"
+    "q_proj",
+    "gate_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:d73bf4ce177393471d952d35b33da217f75addbdae39b3a871687cccf3b3ce39
+oid sha256:795e2e3c0e5a54fbcc6e2442108864a70cc6e0289844570fbf84185fe26ef7b6
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1360b214dc305ce0c7fca0fdb3feecc9d03ca3af798b10af45b117b0f4bff123
+oid sha256:5d0ba80f16c2c94e21775a2856af67517c490b5afe3b70fa1114b06962e15827
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a07e515bbe51ee7462625a205258718fb40294cf374a221ad7132be018d952
+oid sha256:6490e5a3cff06e318976079f975119211253e986d6a187c4f54d9d8791c8da19
 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": 0.00036000360003600034,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004680046800468005,
+  "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": 0.00036000360003600034,
       "eval_loss": NaN,
-      "eval_runtime": 126.1868,
-      "eval_samples_per_second": 9.272,
-      "eval_steps_per_second": 4.636,
+      "eval_runtime": 126.2277,
+      "eval_samples_per_second": 9.269,
+      "eval_steps_per_second": 4.634,
       "step": 1
+    },
+    {
+      "epoch": 0.0018000180001800019,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0036000360003600037,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0036000360003600037,
+      "eval_loss": NaN,
+      "eval_runtime": 125.1626,
+      "eval_samples_per_second": 9.348,
+      "eval_steps_per_second": 4.674,
+      "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": 348527209218048.0,
+  "total_flos": 4487287818682368.0,
   "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 sha256:553e9f88f1c9b4f009e4a36f4544b8f080365b049b238b02f026ebb0ea2679bc
+oid sha256:6ae05755ff458fc6da7fc01d2a0d6f4383102fe766ea17708d98699d44eafd14
 size 6776