Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
-    "o_proj",
     "gate_proj",
     "k_proj",
     "v_proj",
-    "q_proj"
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "down_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 sha256:16e9cc6aab1c6fab8a0e8bfbfd4580af8f7353eb383d62ec9a5c46ce6adb0af4
+oid sha256:a3535b272c3329c46e00c9205e93883f3287bbe2edaede2bcdc6156f830e718a
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a874e8b881a7ca30178641c2e5465ea979e63c5380d970b43bc524e439e3d788
+oid sha256:e593054c916c6dd9eaa4492a5c8d45be70d185bab9df43301eae3820064b6aa9
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2eae9201856a338feeba0ff4bf7474692709b21fd9c0fc9f43cf11e5b83198f
+oid sha256:9c33c2aa5717a7411ca615f356d28027e636bc6c5fac57f90a9e4918f7b5fd41
 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": 0.0007356998344675372,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.009564097848077983,
+  "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": 0.0007356998344675372,
       "eval_loss": 5.8742570877075195,
-      "eval_runtime": 70.5006,
-      "eval_samples_per_second": 8.128,
-      "eval_steps_per_second": 4.071,
+      "eval_runtime": 70.8587,
+      "eval_samples_per_second": 8.087,
+      "eval_steps_per_second": 4.05,
       "step": 1
+    },
+    {
+      "epoch": 0.0036784991723376862,
+      "grad_norm": 4.493916034698486,
+      "learning_rate": 5e-05,
+      "loss": 6.1495,
+      "step": 5
+    },
+    {
+      "epoch": 0.0073569983446753725,
+      "grad_norm": 4.465775012969971,
+      "learning_rate": 0.0001,
+      "loss": 4.9538,
+      "step": 10
+    },
+    {
+      "epoch": 0.0073569983446753725,
+      "eval_loss": 4.622633934020996,
+      "eval_runtime": 69.7393,
+      "eval_samples_per_second": 8.216,
+      "eval_steps_per_second": 4.115,
+      "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:fa02abfe8bc771b3caa91cebb8efc82370254b60d5a73130274cbf5b84f61cbc
+oid sha256:059c6ea3b04292cf33222bbff78306b487001d0212da18140efec00fe3a62b42
 size 6776