Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,8 +22,8 @@
   "target_modules": [
     "dense_h_to_4h",
     "dense",
-    "dense_4h_to_h",
-    "query_key_value"
+    "query_key_value",
+    "dense_4h_to_h"
   ],
   "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:a447b41234d542f1833b1a3fab1bcfc1e4f76d7dd352292c5addd12fed7cf59a
+oid sha256:831a05b2de8bff44d595e4eaeedcd068524f812043e22d6af9cfae61ec1566a3
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c408423914b6d6e51ebf69546bf8dfd8979ccfa977e8f49ab83287740908b84f
+oid sha256:05fbbe6487db9473901117506832ca43d4992089d9373bdcb7a33072a3795eb5
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97b60998d53c1d797db53e375383a7d6d6df4606d2b68d39abea77130b5c637
+oid sha256:68a99e76e9e47417219f8179b23e11de131005a80a8a0f68835b1c9c0a9a539c
 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": 0.00017146776406035664,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0022290809327846365,
+  "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": 0.00017146776406035664,
       "eval_loss": 4.108325481414795,
-      "eval_runtime": 43.2042,
-      "eval_samples_per_second": 56.846,
-      "eval_steps_per_second": 28.423,
+      "eval_runtime": 43.954,
+      "eval_samples_per_second": 55.877,
+      "eval_steps_per_second": 27.938,
       "step": 1
+    },
+    {
+      "epoch": 0.0008573388203017832,
+      "grad_norm": 42.89037322998047,
+      "learning_rate": 5e-05,
+      "loss": 16.2439,
+      "step": 5
+    },
+    {
+      "epoch": 0.0017146776406035665,
+      "grad_norm": 46.44820785522461,
+      "learning_rate": 0.0001,
+      "loss": 17.8283,
+      "step": 10
+    },
+    {
+      "epoch": 0.0017146776406035665,
+      "eval_loss": 4.063690662384033,
+      "eval_runtime": 43.7981,
+      "eval_samples_per_second": 56.075,
+      "eval_steps_per_second": 28.038,
+      "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": 8772856578048.0,
+  "total_flos": 114047135514624.0,
   "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 sha256:83609ff51288be85df65735c2171d7988abdf69c1a5c8dfd2b8ec173291b43df
+oid sha256:15376abe9b023e420e2f6c724bfe1dd63b80900071fa632836286c0b456efa15
 size 6776