Training in progress, step 22500, checkpoint

last-checkpoint/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": "unsloth",
   "target_modules": [
-    "o_proj",
     "v_proj",
-    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
     "down_proj",
     "gate_proj",
-    "k_proj",
-    "up_proj"
+    "q_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 sha256:663d5a330f089957e1de6503a8a7d1dfeacea9e1c2f46b7b02d963a0e8d4c5b6
+oid sha256:7ccb45568bd4c7d3511e45041d493c661b174070436e88dce1bd20710cc6d9db
 size 5544932128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7648c0b96204cf4fa1e72019b6b76455d10152e948900941d742bc2032cf901c
+oid sha256:72405585c668a525f1558d98e3c21e5e39cecf4124ca419c1d132b5ae8b3dba9
 size 2779550366

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71cd57c0a39c9efff0f951a19c93f1b94133eba860a04cd29141f1a192bb0770
+oid sha256:cd21db90406acf9716c653cef333b46bc65f2d3afa87981f50c21efc9b5dc1a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.42316314450517617,
+  "epoch": 0.9067781667968061,
   "eval_steps": 500,
-  "global_step": 10500,
+  "global_step": 22500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,6 +154,174 @@
       "learning_rate": 3.204737808427746e-05,
       "loss": 0.5001,
       "step": 10500
+    },
+    {
+      "epoch": 0.4433137704339941,
+      "grad_norm": 0.5442752242088318,
+      "learning_rate": 3.092785813443196e-05,
+      "loss": 0.5053,
+      "step": 11000
+    },
+    {
+      "epoch": 0.463464396362812,
+      "grad_norm": 0.5094788074493408,
+      "learning_rate": 2.9808338184586448e-05,
+      "loss": 0.502,
+      "step": 11500
+    },
+    {
+      "epoch": 0.48361502229162995,
+      "grad_norm": 0.5177408456802368,
+      "learning_rate": 2.8688818234740942e-05,
+      "loss": 0.4972,
+      "step": 12000
+    },
+    {
+      "epoch": 0.5037656482204479,
+      "grad_norm": 0.5165345072746277,
+      "learning_rate": 2.756929828489544e-05,
+      "loss": 0.495,
+      "step": 12500
+    },
+    {
+      "epoch": 0.5239162741492658,
+      "grad_norm": 0.6729832291603088,
+      "learning_rate": 2.644977833504993e-05,
+      "loss": 0.4942,
+      "step": 13000
+    },
+    {
+      "epoch": 0.5440669000780837,
+      "grad_norm": 0.5211122035980225,
+      "learning_rate": 2.5330258385204423e-05,
+      "loss": 0.4928,
+      "step": 13500
+    },
+    {
+      "epoch": 0.5642175260069016,
+      "grad_norm": 0.6845284104347229,
+      "learning_rate": 2.421073843535892e-05,
+      "loss": 0.4935,
+      "step": 14000
+    },
+    {
+      "epoch": 0.5843681519357194,
+      "grad_norm": 0.8934305906295776,
+      "learning_rate": 2.3091218485513413e-05,
+      "loss": 0.4889,
+      "step": 14500
+    },
+    {
+      "epoch": 0.6045187778645374,
+      "grad_norm": 0.5098538994789124,
+      "learning_rate": 2.1971698535667904e-05,
+      "loss": 0.4863,
+      "step": 15000
+    },
+    {
+      "epoch": 0.6246694037933553,
+      "grad_norm": 0.7277902364730835,
+      "learning_rate": 2.0852178585822403e-05,
+      "loss": 0.4866,
+      "step": 15500
+    },
+    {
+      "epoch": 0.6448200297221732,
+      "grad_norm": 0.5824995040893555,
+      "learning_rate": 1.9732658635976894e-05,
+      "loss": 0.4872,
+      "step": 16000
+    },
+    {
+      "epoch": 0.6649706556509911,
+      "grad_norm": 0.5100158452987671,
+      "learning_rate": 1.861313868613139e-05,
+      "loss": 0.4891,
+      "step": 16500
+    },
+    {
+      "epoch": 0.6851212815798091,
+      "grad_norm": 0.7346712946891785,
+      "learning_rate": 1.7493618736285884e-05,
+      "loss": 0.4819,
+      "step": 17000
+    },
+    {
+      "epoch": 0.705271907508627,
+      "grad_norm": 0.805208146572113,
+      "learning_rate": 1.6374098786440375e-05,
+      "loss": 0.4805,
+      "step": 17500
+    },
+    {
+      "epoch": 0.7254225334374449,
+      "grad_norm": 0.6093766093254089,
+      "learning_rate": 1.5254578836594868e-05,
+      "loss": 0.4816,
+      "step": 18000
+    },
+    {
+      "epoch": 0.7455731593662628,
+      "grad_norm": 0.5469486117362976,
+      "learning_rate": 1.4135058886749365e-05,
+      "loss": 0.4815,
+      "step": 18500
+    },
+    {
+      "epoch": 0.7657237852950808,
+      "grad_norm": 0.6185249090194702,
+      "learning_rate": 1.3015538936903856e-05,
+      "loss": 0.4823,
+      "step": 19000
+    },
+    {
+      "epoch": 0.7858744112238987,
+      "grad_norm": 0.6320446133613586,
+      "learning_rate": 1.189601898705835e-05,
+      "loss": 0.48,
+      "step": 19500
+    },
+    {
+      "epoch": 0.8060250371527166,
+      "grad_norm": 0.7233290672302246,
+      "learning_rate": 1.0776499037212844e-05,
+      "loss": 0.4776,
+      "step": 20000
+    },
+    {
+      "epoch": 0.8261756630815345,
+      "grad_norm": 0.5041834115982056,
+      "learning_rate": 9.656979087367337e-06,
+      "loss": 0.4758,
+      "step": 20500
+    },
+    {
+      "epoch": 0.8463262890103523,
+      "grad_norm": 0.5525909066200256,
+      "learning_rate": 8.53745913752183e-06,
+      "loss": 0.4748,
+      "step": 21000
+    },
+    {
+      "epoch": 0.8664769149391703,
+      "grad_norm": 0.493874192237854,
+      "learning_rate": 7.417939187676325e-06,
+      "loss": 0.4789,
+      "step": 21500
+    },
+    {
+      "epoch": 0.8866275408679882,
+      "grad_norm": 0.4965188205242157,
+      "learning_rate": 6.298419237830819e-06,
+      "loss": 0.4736,
+      "step": 22000
+    },
+    {
+      "epoch": 0.9067781667968061,
+      "grad_norm": 0.5210591554641724,
+      "learning_rate": 5.178899287985312e-06,
+      "loss": 0.4782,
+      "step": 22500
     }
   ],
   "logging_steps": 500,
@@ -173,7 +341,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.677250108543338e+19,
+  "total_flos": 3.5951230851136782e+19,
   "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 sha256:4bfe1550ddce5e600f8af695537ba4b034ec5ea1be78e55ddc34720ae0669092
-size 5176
+oid sha256:fc31d462bd82ad45ffcdb48c070e8e8357be08cdb71164ba74143674f9a54e04
+size 5112