Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj",
     "up_proj",
+    "q_proj",
     "o_proj",
-    "v_proj"
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "k_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 sha256:623e21be8d454f810392a7a1ce83316f345e6476e368029f36d1cae640906eb5
+oid sha256:e96559486e433ef71274858290ea24a9fb89facc4d3b2d4a9bab9d21dbb57a68
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19cb011e6e67803346cf79ce198a1005783b77bc4c591ef75e1e77295da36ac
+oid sha256:7a1080c9d277b85afcbb5a7d4774379c5dcb6b3df9a38625b087fef3c6c876b1
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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": 0.0006096631611034903,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007925621094345374,
+  "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": 0.0006096631611034903,
       "eval_loss": NaN,
-      "eval_runtime": 158.2806,
-      "eval_samples_per_second": 4.366,
-      "eval_steps_per_second": 2.186,
+      "eval_runtime": 164.583,
+      "eval_samples_per_second": 4.198,
+      "eval_steps_per_second": 2.102,
       "step": 1
+    },
+    {
+      "epoch": 0.0030483158055174516,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.006096631611034903,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.006096631611034903,
+      "eval_loss": NaN,
+      "eval_runtime": 163.5264,
+      "eval_samples_per_second": 4.226,
+      "eval_steps_per_second": 2.116,
+      "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": 164316422602752.0,
+  "total_flos": 2136113493835776.0,
   "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:a467b8d5dbe8772a622b26a0c3cc9a6ceb84c08c1a960abf6e43ff08b1f63ec2
+oid sha256:61ad6dfc8d97b7276ea8cc21f7b574a2c945dabd1eae6cd5c7cb045f27df5750
 size 6776