Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
+    "k_proj",
     "gate_proj",
     "o_proj",
     "q_proj",
-    "down_proj",
-    "k_proj"
+    "up_proj",
+    "v_proj",
+    "down_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:b3e000c5d92a63be69983b834ca3299dc4badae9f321ff784442ebfe67903c2d
+oid sha256:5821dc1648635c8aa03b9ca13334906fe375c0cc3d6f0e536906be10a24d619c
 size 1770585648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a381d4a2a2d0670d71222c413fc4d92c5726eb357d5cca7876c0c89802b0db7
+oid sha256:e93e8b2ee985e5752fbe82f4da680ce3cf6b58db11054bc35cea1c1df8195307
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e22fba92b29c1f5f0cd59a19fdf634f506ef846ae85ca8af68d60096387010
+oid sha256:d6a216e76306077697fce369babc722d934631ceab06c507d0d26aa9b1335b22
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,114 +1,63 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.042105263157894736,
+  "epoch": 0.021052631578947368,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.004210526315789474,
-      "grad_norm": 4.255664348602295,
+      "grad_norm": 6.040051460266113,
       "learning_rate": 2e-05,
-      "loss": 4.8197,
+      "loss": 5.2097,
       "step": 1
     },
     {
       "epoch": 0.004210526315789474,
-      "eval_loss": 4.639376640319824,
-      "eval_runtime": 33.5525,
-      "eval_samples_per_second": 2.98,
-      "eval_steps_per_second": 1.49,
+      "eval_loss": 5.1479387283325195,
+      "eval_runtime": 33.4641,
+      "eval_samples_per_second": 2.988,
+      "eval_steps_per_second": 1.494,
       "step": 1
     },
     {
       "epoch": 0.008421052631578947,
-      "grad_norm": 4.722397804260254,
+      "grad_norm": 6.306079387664795,
       "learning_rate": 4e-05,
-      "loss": 4.7099,
+      "loss": 5.1825,
       "step": 2
     },
     {
       "epoch": 0.01263157894736842,
-      "grad_norm": 4.832592964172363,
+      "grad_norm": 6.255680561065674,
       "learning_rate": 6e-05,
-      "loss": 4.6489,
+      "loss": 5.2103,
       "step": 3
     },
     {
       "epoch": 0.01263157894736842,
-      "eval_loss": 4.5546650886535645,
-      "eval_runtime": 33.7836,
-      "eval_samples_per_second": 2.96,
-      "eval_steps_per_second": 1.48,
+      "eval_loss": 5.074653625488281,
+      "eval_runtime": 33.571,
+      "eval_samples_per_second": 2.979,
+      "eval_steps_per_second": 1.489,
       "step": 3
     },
     {
       "epoch": 0.016842105263157894,
-      "grad_norm": 5.204955101013184,
+      "grad_norm": 6.213514804840088,
       "learning_rate": 8e-05,
-      "loss": 5.0702,
+      "loss": 5.0592,
       "step": 4
     },
     {
       "epoch": 0.021052631578947368,
-      "grad_norm": 6.269968509674072,
+      "grad_norm": 6.902180194854736,
       "learning_rate": 0.0001,
-      "loss": 4.7515,
+      "loss": 4.7818,
       "step": 5
-    },
-    {
-      "epoch": 0.02526315789473684,
-      "grad_norm": 5.368188858032227,
-      "learning_rate": 0.00012,
-      "loss": 4.0712,
-      "step": 6
-    },
-    {
-      "epoch": 0.02526315789473684,
-      "eval_loss": 2.9871139526367188,
-      "eval_runtime": 33.7582,
-      "eval_samples_per_second": 2.962,
-      "eval_steps_per_second": 1.481,
-      "step": 6
-    },
-    {
-      "epoch": 0.029473684210526315,
-      "grad_norm": 5.832278251647949,
-      "learning_rate": 0.00014,
-      "loss": 2.9739,
-      "step": 7
-    },
-    {
-      "epoch": 0.03368421052631579,
-      "grad_norm": 6.239769458770752,
-      "learning_rate": 0.00016,
-      "loss": 2.2879,
-      "step": 8
-    },
-    {
-      "epoch": 0.037894736842105266,
-      "grad_norm": 4.585263729095459,
-      "learning_rate": 0.00018,
-      "loss": 1.3689,
-      "step": 9
-    },
-    {
-      "epoch": 0.037894736842105266,
-      "eval_loss": 1.0050288438796997,
-      "eval_runtime": 33.7547,
-      "eval_samples_per_second": 2.963,
-      "eval_steps_per_second": 1.481,
-      "step": 9
-    },
-    {
-      "epoch": 0.042105263157894736,
-      "grad_norm": 1.368607759475708,
-      "learning_rate": 0.0002,
-      "loss": 1.1466,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +72,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5637488844472320.0,
+  "total_flos": 2818744422236160.0,
   "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 sha256:5445be5af6e5cce1c20124d4cf61b3d92a04c22b6582877f2034e8c5cffc8146
+oid sha256:5c065ec84dd21be97f3fe967534a1ead46d2026c2a8b5c2052b5b9b23339df95
 size 6136