Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "k_proj",
-    "o_proj",
+    "gate_proj",
     "down_proj",
-    "v_proj",
     "q_proj",
-    "gate_proj"
+    "o_proj",
+    "v_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 sha256:7dd4cc4c71a940a89a65a3f432aacabe8460e7af6f7f7ca1853c421ba6238ebe
+oid sha256:1a36366047a02a652bf0d9a948a821be23bfbce66837a5b39bd8ec77c3db8615
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f845a95ae29d677de13c3f6493c0c40f0aee1880afcd129286713a3c4012eaf0
+oid sha256:1ef4486e6cf85b13ec5addf50a68fe006978ad627ef260994c6245920142afa9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 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": 1.9636238678481137e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00025527110282025475,
+  "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": 1.9636238678481137e-05,
       "eval_loss": 2.0113277435302734,
-      "eval_runtime": 1446.7011,
-      "eval_samples_per_second": 14.822,
-      "eval_steps_per_second": 7.411,
+      "eval_runtime": 1445.8125,
+      "eval_samples_per_second": 14.831,
+      "eval_steps_per_second": 7.416,
       "step": 1
+    },
+    {
+      "epoch": 9.818119339240569e-05,
+      "grad_norm": 1.4396002292633057,
+      "learning_rate": 5e-05,
+      "loss": 2.0312,
+      "step": 5
+    },
+    {
+      "epoch": 0.00019636238678481137,
+      "grad_norm": 1.684613585472107,
+      "learning_rate": 0.0001,
+      "loss": 1.7131,
+      "step": 10
+    },
+    {
+      "epoch": 0.00019636238678481137,
+      "eval_loss": 1.2434030771255493,
+      "eval_runtime": 1450.4983,
+      "eval_samples_per_second": 14.783,
+      "eval_steps_per_second": 7.392,
+      "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": 184956424814592.0,
+  "total_flos": 2404433522589696.0,
   "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 sha256:90cdd9590539d0130d8df960b9af840313d0b03a2cdb9f27e736a483e5aa85bb
+oid sha256:a87375fea3ada72b707ef018ead138e066e8377e20dea7fac33c943fcf4908c0
 size 6776