Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
     "gate_proj",
+    "down_proj",
     "q_proj",
-    "o_proj",
     "up_proj",
-    "v_proj"
+    "v_proj",
+    "o_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:a3dd33c2ffa6ecbb3522e031f93667e2b1fb84ddf4c3faffd5040c642a5cd8c4
+oid sha256:9a3e8f7d8fd1815dae0a3b98fc21ced39447f7614611cb84291f1ad0c6705773
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2c8cdcb4f6604d9106180f7670371da07374bbc9bd8b784d5eb25145961552
+oid sha256:b2b24e0811a6953353e3e1b5e43d17062ebca118f6f099bcea7dd8e6bf8a901c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:3f0082b9ee265cb0c6910d3944f6a738794d996da2e7f7ac5ed1f97dde094437
 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": 0.0003719546215361726,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004835410079970244,
+  "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": 0.0003719546215361726,
       "eval_loss": 2.958796739578247,
-      "eval_runtime": 102.1389,
-      "eval_samples_per_second": 11.083,
-      "eval_steps_per_second": 5.541,
+      "eval_runtime": 101.9058,
+      "eval_samples_per_second": 11.108,
+      "eval_steps_per_second": 5.554,
       "step": 1
+    },
+    {
+      "epoch": 0.001859773107680863,
+      "grad_norm": 60.900169372558594,
+      "learning_rate": 5e-05,
+      "loss": 11.3994,
+      "step": 5
+    },
+    {
+      "epoch": 0.003719546215361726,
+      "grad_norm": 40.15205001831055,
+      "learning_rate": 0.0001,
+      "loss": 8.9652,
+      "step": 10
+    },
+    {
+      "epoch": 0.003719546215361726,
+      "eval_loss": 1.8373997211456299,
+      "eval_runtime": 107.9048,
+      "eval_samples_per_second": 10.491,
+      "eval_steps_per_second": 5.245,
+      "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": 175267179921408.0,
+  "total_flos": 2409923723919360.0,
   "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:c6d8ed82545866528ef571319d66ad31efbffe082e9012110982f054752c5126
+oid sha256:ca12b8ad431d40a68a0b733ffa185d7149708a90231f216d60661f6316f08af9
 size 6776