Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "o_proj",
-    "k_proj",
     "q_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
     "down_proj",
-    "gate_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:b80e4146c034f98af19312e362f5d5b11a6c104275c7052a21eccae133c15456
+oid sha256:47dc1fbbd5669ac94b72b9f6ff93d9d44ee13d9d3f4c0df0a23df0675fb70034
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe7fe1be28e72d7e4120be236a176e0c98a5d22cea5ba4029ad99244a702cd0
+oid sha256:e0fed541ec9fa7a453fb4383a792ebe4e380cb5cf0416f635b24d6d6d0ae9d78
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc6a8a8efd64189f83fbd5af595229bb3855f838cf75dfff2c5739d83ac84b2
+oid sha256:0d5b557f9ac731f277d55c777bf769719d64b454cd4a996ecd46ec39906e6568
 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": 0.0064282844515869825,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.08356769787063077,
+  "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": 0.0064282844515869825,
       "eval_loss": 2.085723400115967,
-      "eval_runtime": 38.1106,
-      "eval_samples_per_second": 27.499,
-      "eval_steps_per_second": 3.437,
+      "eval_runtime": 38.4863,
+      "eval_samples_per_second": 27.23,
+      "eval_steps_per_second": 3.404,
       "step": 1
+    },
+    {
+      "epoch": 0.06428284451586982,
+      "grad_norm": 0.21534493565559387,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 2.0586,
+      "step": 10
+    },
+    {
+      "epoch": 0.06428284451586982,
+      "eval_loss": 2.0195319652557373,
+      "eval_runtime": 38.3787,
+      "eval_samples_per_second": 27.307,
+      "eval_steps_per_second": 3.413,
+      "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": 1252301482229760.0,
+  "total_flos": 1.662778079182848e+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:a5b477fcf81053b40d0d73ad9cb0e7c26ac0eacf1aeba25a2f723015491ab0e3
+oid sha256:dbb33c66f9c4d292d2694d3e0127bbc61a86a33fc7b3dd71857ee2e66358815b
 size 6776