Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "v_proj",
     "k_proj",
-    "up_proj",
-    "gate_proj",
     "down_proj",
     "o_proj",
-    "v_proj"
+    "gate_proj",
+    "q_proj",
+    "up_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:ae847da4aca3d790b65ab4f39563fb40364b79ffed552fe0826017243f6e30ec
+oid sha256:b6e9d607952ee7dcc348aeac88985c903f67300c26e492221d181eb9b74e3b9c
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8839b84d26e420215c98b4cd830fbc3cec3af17f40b7a811b50dab37c5efea
+oid sha256:e362589fc8ac3dbb7f4fc8e85aec02a970d8400f651b3c6883fde1888133ef16
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17cd0b5f1e33bd6dba2461570a653efdaf1fb902096b4df09992935b3fc24a4
+oid sha256:dc12b3ebfd598da93336aea3b9e623a1adcbdea90c1ade145e09bc2a56a621b5
 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": 5.0911960492318656e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0006618554864001425,
+  "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": 5.0911960492318656e-05,
       "eval_loss": 3.2041211128234863,
-      "eval_runtime": 277.8809,
-      "eval_samples_per_second": 29.765,
-      "eval_steps_per_second": 14.884,
+      "eval_runtime": 273.0403,
+      "eval_samples_per_second": 30.292,
+      "eval_steps_per_second": 15.148,
       "step": 1
+    },
+    {
+      "epoch": 0.0002545598024615933,
+      "grad_norm": 3.1962180137634277,
+      "learning_rate": 5e-05,
+      "loss": 2.8082,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005091196049231866,
+      "grad_norm": 2.8137855529785156,
+      "learning_rate": 0.0001,
+      "loss": 3.1394,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005091196049231866,
+      "eval_loss": 2.8642525672912598,
+      "eval_runtime": 273.8633,
+      "eval_samples_per_second": 30.201,
+      "eval_steps_per_second": 15.102,
+      "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": 8903816380416.0,
+  "total_flos": 115749612945408.0,
   "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 sha256:30cb52c679aa9995237e3697b8da756ef6b77124b3fafe9ce94720165e3801ab
+oid sha256:b366b582011d1cbdc4a2e78d97f19bbf28cb698e9080746e4a5b66972e0c2104
 size 6776