Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "v_proj",
     "up_proj",
-    "gate_proj",
-    "o_proj",
     "down_proj",
+    "gate_proj",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "o_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 sha256:05d37a02642e4bf2363d482bf2714d0caf59a64cd6d2dc4467f71cbf963607a5
+oid sha256:40b0d9600544e51cd654c4caaa5cb3d7a7ab83431c41d91c929b9ffb5f51fa92
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:47c4b1b1022476a667133913254b988ff83885ee227e03c4f7dc228d6177ea10
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e21a82df0c35618a9fae460cd44f4d0de4f06c7436e3176c977454ef6f7d54b5
+oid sha256:7d9013a79d67ddcb6d9d32a487da5e5f304f6d20307ca065e25b775a6da9df05
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013745704467353952,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.17869415807560138,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.013745704467353952,
       "eval_loss": NaN,
-      "eval_runtime": 17.8672,
-      "eval_samples_per_second": 27.425,
-      "eval_steps_per_second": 3.47,
+      "eval_runtime": 18.0815,
+      "eval_samples_per_second": 27.1,
+      "eval_steps_per_second": 3.429,
       "step": 1
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "eval_loss": NaN,
+      "eval_runtime": 16.4273,
+      "eval_samples_per_second": 29.828,
+      "eval_steps_per_second": 3.774,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 875605297987584.0,
+  "total_flos": 1.1545018003095552e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f6a4ea48b14e685ca5ae09e49ffaa30b4fedc1dd8e8e65f6133df6108c6668
+oid sha256:2c3b5a0bcf273e34cf0a7149b3e71ce068be0676f316b2893a38223f0e045a60
 size 6776