Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "gate_proj",
-    "k_proj",
-    "o_proj",
     "v_proj",
+    "up_proj",
+    "gate_proj",
     "q_proj",
-    "up_proj"
+    "k_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:ff221be6b8de2a5d359ff88e3782a0401557faef60fd1c0e4f2f44a5adeace2e
+oid sha256:abb170f4eb21646db6da17b4cf06241d404c593d56772ab194e4bccc4dd1cb07
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7640f663eee7eb42c3a194498143bf9eb1310dd8d0c0c8bacf9a9845e1390a1
+oid sha256:98e7e9bc3f8ca023b4097d5fe32e80741f85bb5eaebd7b5df2a8110eec60bf91
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f2b1fe1ee433d0949425d85cbc1e7db562c93cb1fc4f9c675368fbffc7b15d
+oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
 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": 1.3361793954456326e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00017370332140793224,
+  "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": 1.3361793954456326e-05,
       "eval_loss": 2.251216411590576,
-      "eval_runtime": 1003.1511,
-      "eval_samples_per_second": 31.413,
-      "eval_steps_per_second": 15.707,
+      "eval_runtime": 964.0542,
+      "eval_samples_per_second": 32.687,
+      "eval_steps_per_second": 16.343,
       "step": 1
+    },
+    {
+      "epoch": 6.680896977228163e-05,
+      "grad_norm": 16.5920467376709,
+      "learning_rate": 5e-05,
+      "loss": 2.0823,
+      "step": 5
+    },
+    {
+      "epoch": 0.00013361793954456326,
+      "grad_norm": 9.915910720825195,
+      "learning_rate": 0.0001,
+      "loss": 1.7611,
+      "step": 10
+    },
+    {
+      "epoch": 0.00013361793954456326,
+      "eval_loss": 1.591361165046692,
+      "eval_runtime": 978.1758,
+      "eval_samples_per_second": 32.215,
+      "eval_steps_per_second": 16.108,
+      "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": 25579197825024.0,
+  "total_flos": 332529571725312.0,
   "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 sha256:7f7f5a65aae1403b6912b1a44968303f1707a506223f7984868c8c387d8ef7da
+oid sha256:82c09c574adebdd24e0fa5410a0e67f087c2fe06704fd88fba78eecb64c6d757
 size 6776