Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "o_proj",
-    "k_proj",
-    "q_proj",
     "up_proj",
     "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_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 sha256:132a110701ed84e4139d2e078e59b4fbfd1d09c11643f3c5c158cae5b19ed5ae
+oid sha256:1f40a19e6be9ca5ebd3d6d620579fed31ae7d3aeb2ab8111fad9504c99a6b572
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92abd9d734113415fca3f67740d0ef88665ec93aadd0e9da0cf72b4ce4c22d20
+oid sha256:c10812aa378b65d333e79585f549c1adb20a0e427b72f5bf8488ee91b60979ea
 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": 0.003898635477582846,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.050682261208576995,
+  "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": 0.003898635477582846,
       "eval_loss": 0.9151607751846313,
-      "eval_runtime": 12.8368,
-      "eval_samples_per_second": 8.413,
-      "eval_steps_per_second": 4.207,
+      "eval_runtime": 12.8201,
+      "eval_samples_per_second": 8.424,
+      "eval_steps_per_second": 4.212,
       "step": 1
+    },
+    {
+      "epoch": 0.01949317738791423,
+      "grad_norm": 8.332606315612793,
+      "learning_rate": 5e-05,
+      "loss": 3.4517,
+      "step": 5
+    },
+    {
+      "epoch": 0.03898635477582846,
+      "grad_norm": 5.3900651931762695,
+      "learning_rate": 0.0001,
+      "loss": 2.8376,
+      "step": 10
+    },
+    {
+      "epoch": 0.03898635477582846,
+      "eval_loss": 0.6592496037483215,
+      "eval_runtime": 12.9746,
+      "eval_samples_per_second": 8.324,
+      "eval_steps_per_second": 4.162,
+      "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:aea809bb9d543154e60b27f4665ab1d8690e596140ee7344a4d42ed174354303
+oid sha256:4f2051f113ba1422e02b51f39e4c81af564ffd9322af8adcdf15642ebda43773
 size 6776