Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
-    "q_proj",
     "o_proj",
+    "gate_proj",
+    "v_proj",
     "up_proj",
+    "down_proj",
     "k_proj",
-    "gate_proj"
+    "q_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:fe3975c913f61d80703fb1fdd4b00bd06b4ee86bae87d29889ed62b15cf9b434
+oid sha256:ee710b8dd906183938c5b63213859483c17ee21935fb919940e76c83fab37930
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a18bc893d519f6cafd3b37cd870fe74e8284e874127a358828d4a6c5907059c
+oid sha256:adf17d75a4de795ea961fc373e7b95121017db67440e0b5ef919551ae10ae932
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:e1ec4ef3d50e123d7d669b070b9f893b4d6814e6a83307723fb238005cad1152
 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": 0.0014503263234227702,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01885424220449601,
+  "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": 0.0014503263234227702,
       "eval_loss": 0.2840324938297272,
-      "eval_runtime": 26.3366,
-      "eval_samples_per_second": 11.049,
-      "eval_steps_per_second": 5.544,
+      "eval_runtime": 26.3496,
+      "eval_samples_per_second": 11.044,
+      "eval_steps_per_second": 5.541,
       "step": 1
+    },
+    {
+      "epoch": 0.007251631617113851,
+      "grad_norm": 7.322425842285156,
+      "learning_rate": 5e-05,
+      "loss": 0.9639,
+      "step": 5
+    },
+    {
+      "epoch": 0.014503263234227702,
+      "grad_norm": 6.449563980102539,
+      "learning_rate": 0.0001,
+      "loss": 0.6865,
+      "step": 10
+    },
+    {
+      "epoch": 0.014503263234227702,
+      "eval_loss": 0.18034805357456207,
+      "eval_runtime": 26.6312,
+      "eval_samples_per_second": 10.927,
+      "eval_steps_per_second": 5.482,
+      "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": 219083723243520.0,
+  "total_flos": 3198622359355392.0,
   "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 sha256:4cb95b2b5588b65517f67fba29335b8c4be38bb94054b241006d34ae3e5296ed
+oid sha256:ca307cbf4c16c826c1f33ad0e78b1339649616955569813d152c4cfe5b0fd794
 size 6776