Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "k_proj",
     "q_proj",
     "down_proj",
-    "o_proj",
-    "up_proj",
     "v_proj",
-    "k_proj",
-    "gate_proj"
+    "o_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 sha256:04bb334ff4e5a8e2ab22dd9cf57014a942b36929a1f73598b0d261698874f970
+oid sha256:8ae543e622735654163a835b5d09870835f0c17be164371d57e1bf6f5a881a12
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df4b4d8a1836cb979b2d2fb824710dc70326a033117a81637b475fa5df3e9597
+oid sha256:811486cabffea9c0b7f51c6bb4f8a77c10060f5413635a610e71eaddbf9cbc2f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:6b8f0aa4af7093e810b0c7cb148aec740829a8c9ba7fcee1f5bd39e83d3fc49a
 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": 0.0001620285980475554,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00210637177461822,
+  "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": 0.0001620285980475554,
       "eval_loss": 2.3156306743621826,
-      "eval_runtime": 316.8318,
-      "eval_samples_per_second": 8.203,
-      "eval_steps_per_second": 4.103,
+      "eval_runtime": 316.9863,
+      "eval_samples_per_second": 8.199,
+      "eval_steps_per_second": 4.101,
       "step": 1
+    },
+    {
+      "epoch": 0.000810142990237777,
+      "grad_norm": 1.3373298645019531,
+      "learning_rate": 5e-05,
+      "loss": 2.1229,
+      "step": 5
+    },
+    {
+      "epoch": 0.001620285980475554,
+      "grad_norm": 1.4930287599563599,
+      "learning_rate": 0.0001,
+      "loss": 2.2211,
+      "step": 10
+    },
+    {
+      "epoch": 0.001620285980475554,
+      "eval_loss": 2.0873374938964844,
+      "eval_runtime": 319.8042,
+      "eval_samples_per_second": 8.127,
+      "eval_steps_per_second": 4.065,
+      "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": 369912849629184.0,
+  "total_flos": 4716388832772096.0,
   "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:d13202b48d9e64c9458f89199dfb02f936618265728441eab5f6d5c1bbd887d5
+oid sha256:13a84d231ac063df6978bc9b05d85a5336a7a0ef1949e105f370240d67d0beb6
 size 6776