Training in progress, step 15, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "up_proj",
-    "down_proj",
-    "gate_proj",
     "o_proj",
-    "q_proj",
-    "k_proj"
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_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 sha256:56736da540e8c0936ddcb0782690cac58466eab2b768309f1b847eb9f83d0d9b
+oid sha256:c3082c505a3ed59c4fbee141f8ee238b44b6ac99afc4adb7f9bce814e49a7b4a
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f11a33ee7c3186996e7c295c3b8ee106f2c84067908c6aff9b293efd027a95
+oid sha256:27a2b5521e5ccd05ba0344bf8ec6ae8ea4774ab5a70df9a65cbe6f57eb4ccb10
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4795d4ea56c7bbad5211d2c89fae5345ee850d3d5c0e1e07519d9a59aa43f322
+oid sha256:6b6818a44327baca2f62f7480d744e23c8e48485d5cc6712a060c92df637850b
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdcaa7acd195c38164b4cfbf58785ff6734ceab7758dfdb61896569eab8b07e5
+oid sha256:08a83c8131db177581c328e72cdf50c048d4ace8dd5c8da5db507adefb502530
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa69e4ebb63bfeb4e88c45801fdb42750a3fa6277fe4f9fe4d56ed19c32d86b
+oid sha256:0aef13fcaa9c11b2ff403f94c1cdc53687b12672d25dc788dff398dc814ac325
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c92eb97aacc162626fcb37b2a08d27a4a6c62b113bfc34d97fe5ad2f725325d
+oid sha256:dae48d4c20573f244a234c5908e300f1d4f979f25df3d23f79718ac9899d5e7c
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc1f4d4a90d2a47485c2a01cffea2c7d0aa965cc37c7bc4811695e15285c17c
+oid sha256:7db73e8ba9e52e2cda7fd0517f655ef1cceb7c2e0b2230076162db088e9aebee
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6218d3540a34000a8339db820d471f0c6f72898d0cff5ecf14b16071095f7ada
+oid sha256:eff3ff7be8c81654b7f7487e8cac92c81bd8f7936a1a2ce6a69ff32d9f1362a6
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848af25dd310dd5e992dbdcc38b72c78ef73ba9fb01fdb9bdd954d67598d92cd
+oid sha256:b168261fc3a41accdca3740fe30ec4ff4ad80baa9f3c310234f21b23d2bccdd8
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960b66ac8b1d130aa6b93ee5269727c03e2b6a2b28c32a2440608aaf0bf6fd20
+oid sha256:57751c88c0c4bc5bf818be4acf657342366cd129c785f8722d97d25a41a7f863
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
+oid sha256:eae4efc55c9429b91bdc581cf21d4d1e88799c56c267a0959f657aba014828bf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028268551236749116,
+  "epoch": 0.04240282685512368,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0028268551236749115,
       "eval_loss": 7.129258632659912,
-      "eval_runtime": 20.9973,
-      "eval_samples_per_second": 28.385,
-      "eval_steps_per_second": 3.572,
+      "eval_runtime": 13.6697,
+      "eval_samples_per_second": 43.6,
+      "eval_steps_per_second": 5.487,
       "step": 1
     },
     {
@@ -32,14 +32,14 @@
     },
     {
       "epoch": 0.008480565371024734,
-      "grad_norm": 5.082520484924316,
+      "grad_norm": 5.114774703979492,
       "learning_rate": 2e-05,
       "loss": 7.4669,
       "step": 3
     },
     {
       "epoch": 0.011307420494699646,
-      "grad_norm": 4.920047760009766,
+      "grad_norm": 4.991275310516357,
       "learning_rate": 4e-05,
       "loss": 7.1521,
       "step": 4
@@ -48,59 +48,102 @@
       "epoch": 0.014134275618374558,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 7.7426,
+      "loss": 7.7429,
       "step": 5
     },
     {
       "epoch": 0.014134275618374558,
-      "eval_loss": 7.097348213195801,
-      "eval_runtime": 20.8903,
-      "eval_samples_per_second": 28.53,
-      "eval_steps_per_second": 3.59,
+      "eval_loss": 7.097643852233887,
+      "eval_runtime": 20.7137,
+      "eval_samples_per_second": 28.773,
+      "eval_steps_per_second": 3.621,
       "step": 5
     },
     {
       "epoch": 0.01696113074204947,
-      "grad_norm": 4.500086784362793,
+      "grad_norm": 4.559197902679443,
       "learning_rate": 6e-05,
-      "loss": 7.1859,
+      "loss": 7.1861,
       "step": 6
     },
     {
       "epoch": 0.019787985865724382,
-      "grad_norm": 3.6024482250213623,
+      "grad_norm": 3.6284019947052,
       "learning_rate": 8e-05,
-      "loss": 6.9672,
+      "loss": 6.9673,
       "step": 7
     },
     {
       "epoch": 0.022614840989399292,
-      "grad_norm": 4.331362724304199,
+      "grad_norm": 4.3491082191467285,
       "learning_rate": 0.0001,
-      "loss": 7.2915,
+      "loss": 7.2919,
       "step": 8
     },
     {
       "epoch": 0.025441696113074206,
-      "grad_norm": 3.071237564086914,
+      "grad_norm": 3.08682918548584,
       "learning_rate": 0.00012,
-      "loss": 7.2579,
+      "loss": 7.258,
       "step": 9
     },
     {
       "epoch": 0.028268551236749116,
-      "grad_norm": 3.218928813934326,
+      "grad_norm": 3.268092393875122,
       "learning_rate": 0.00014,
-      "loss": 7.0417,
+      "loss": 7.0434,
       "step": 10
     },
     {
       "epoch": 0.028268551236749116,
-      "eval_loss": 6.332116603851318,
-      "eval_runtime": 20.7973,
-      "eval_samples_per_second": 28.658,
-      "eval_steps_per_second": 3.606,
+      "eval_loss": 6.333721160888672,
+      "eval_runtime": 20.9199,
+      "eval_samples_per_second": 28.49,
+      "eval_steps_per_second": 3.585,
       "step": 10
+    },
+    {
+      "epoch": 0.03109540636042403,
+      "grad_norm": 2.161461114883423,
+      "learning_rate": 0.00016,
+      "loss": 6.1538,
+      "step": 11
+    },
+    {
+      "epoch": 0.03392226148409894,
+      "grad_norm": 2.0395100116729736,
+      "learning_rate": 0.00018,
+      "loss": 6.6144,
+      "step": 12
+    },
+    {
+      "epoch": 0.03674911660777385,
+      "grad_norm": 2.263904094696045,
+      "learning_rate": 0.0002,
+      "loss": 6.1712,
+      "step": 13
+    },
+    {
+      "epoch": 0.039575971731448764,
+      "grad_norm": 1.9835869073867798,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.0672,
+      "step": 14
+    },
+    {
+      "epoch": 0.04240282685512368,
+      "grad_norm": 1.9458274841308594,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.7719,
+      "step": 15
+    },
+    {
+      "epoch": 0.04240282685512368,
+      "eval_loss": 5.498767375946045,
+      "eval_runtime": 20.8896,
+      "eval_samples_per_second": 28.531,
+      "eval_steps_per_second": 3.59,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3204441146589184e+16,
+  "total_flos": 1.989781642805248e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b55d7424e01d2da7c827809f0e75e814ca3307809331f5d1880db7934ea6a65
+oid sha256:676c5b957839737d77485c6332fc96de69385066f3eef0d74b47f677462f11dc
 size 6712