Training in progress, step 20, checkpoint

last-checkpoint/adapter_config.json

@@ -22,10 +22,10 @@
   "target_modules": [
     "o_proj",
     "v_proj",
+    "k_proj",
     "down_proj",
-    "gate_proj",
     "up_proj",
-    "k_proj",
+    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf67b44e2474c435f67e089b4aa5e43482ae7ef4a321e6476cc27cfff4b2cf7e
+oid sha256:2d021bed2dd2ea6cbc23c3a8b867bffdd55f4c368e04d09f17f3b51d4d108b02
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedf9f3eb96dc8e2216acb799cce9a385162c8bd915fad167fc6c7b6c2241efa
+oid sha256:d0a10f7717afa23b44f65a53ebf6cbe2926ef737eccc260d9679810673439d8c
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a75d7f0a1110bb7ddac6881490c0ad001206dbfbcb43220dcaada04d94f78c7
+oid sha256:6eb123811012c3e65fe8210f1d274be2778d1e0bf65dd0aabdcb52d45a965673
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44d91ef34966a9236815f68477ab8b7c0e58ef42a28a5a22af7e3d0cde110f8
+oid sha256:52ff37e0b7f3f7b71f4a6c191c0fb713c613613ca91530a76baadf0084a0b329
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea15c7c7180fa009ae4e9ae36bc8881b572608ebcc3ce285a7736b0f9095f73
+oid sha256:b16f49d4dbd626ebb142e185596fd67739629219b9fd5830241a10bc99fa8424
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47bdf74ddba6667c73ef9c6fa16a7d1bad165641219424ed3e8eb85032cf718c
+oid sha256:4e9765b6927214cceda69afe124cfb5b6ccdbd3d1a067e366019e5adf8de990f
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2470a144228bd202c07df4002bbd7fcbc4a4222f4d74493ca1edaeff6a93ee
+oid sha256:bb9470682026f925d0e6429c669b16bca29cc22f61f560570b8e693bba9504d9
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c11c326af75c12615a95cec1905a2e8bc00fae99f6eca9757b169af3d765dc5
+oid sha256:b73a0459b19cbbad15ec41c6fcf0fb4fdda0691e831d8eaaf265eb23a79ae5d3
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855a78294165307b2b2b80f48d1cd373054c685f191380eb9daa248b34ff6405
+oid sha256:f9dec753b1fd5549aa956b5592770c32706a915fb60568a63963d48a5121eabf
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82eb7125a98e578fab3e4b9b4b0732f1974838daab66a58369b34c9560151e2d
+oid sha256:87106faea8a82974fc3344adfa48d717fb2c2c1d3ba12deb0443a5b90b2180bb
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d24ba7ec590426989e38648fb3af9ae90cfcee84014eb4dfc33924d7868044
+oid sha256:ae75e092a889d5e969a2ae073023153d014a68766ac86876f11258c486a735da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.053763440860215055,
+  "epoch": 0.07168458781362007,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,132 +18,175 @@
     {
       "epoch": 0.0035842293906810036,
       "eval_loss": 1.371159315109253,
-      "eval_runtime": 8.3908,
-      "eval_samples_per_second": 56.014,
-      "eval_steps_per_second": 7.032,
+      "eval_runtime": 8.0828,
+      "eval_samples_per_second": 58.148,
+      "eval_steps_per_second": 7.299,
       "step": 1
     },
     {
       "epoch": 0.007168458781362007,
-      "grad_norm": 1.1762983798980713,
+      "grad_norm": 1.2307049036026,
       "learning_rate": 2e-05,
       "loss": 1.2685,
       "step": 2
     },
     {
       "epoch": 0.010752688172043012,
-      "grad_norm": 0.999072253704071,
+      "grad_norm": 1.0430188179016113,
       "learning_rate": 4e-05,
       "loss": 1.1567,
       "step": 3
     },
     {
       "epoch": 0.014336917562724014,
-      "grad_norm": 1.0890846252441406,
+      "grad_norm": 1.1231369972229004,
       "learning_rate": 6e-05,
-      "loss": 1.2905,
+      "loss": 1.29,
       "step": 4
     },
     {
       "epoch": 0.017921146953405017,
-      "grad_norm": 1.1394107341766357,
+      "grad_norm": 1.1865134239196777,
       "learning_rate": 8e-05,
-      "loss": 1.2343,
+      "loss": 1.2327,
       "step": 5
     },
     {
       "epoch": 0.017921146953405017,
-      "eval_loss": 1.3072917461395264,
-      "eval_runtime": 8.5738,
-      "eval_samples_per_second": 54.818,
-      "eval_steps_per_second": 6.881,
+      "eval_loss": 1.304574728012085,
+      "eval_runtime": 8.1943,
+      "eval_samples_per_second": 57.357,
+      "eval_steps_per_second": 7.2,
       "step": 5
     },
     {
       "epoch": 0.021505376344086023,
-      "grad_norm": 1.2360237836837769,
+      "grad_norm": 1.2747498750686646,
       "learning_rate": 0.0001,
-      "loss": 1.4268,
+      "loss": 1.4252,
       "step": 6
     },
     {
       "epoch": 0.025089605734767026,
-      "grad_norm": 0.9018695950508118,
+      "grad_norm": 0.9193595051765442,
       "learning_rate": 0.00012,
-      "loss": 1.0908,
+      "loss": 1.0889,
       "step": 7
     },
     {
       "epoch": 0.02867383512544803,
       "grad_norm": NaN,
       "learning_rate": 0.00012,
-      "loss": 1.4248,
+      "loss": 1.4204,
       "step": 8
     },
     {
       "epoch": 0.03225806451612903,
-      "grad_norm": 0.8699414134025574,
+      "grad_norm": 0.8832981586456299,
       "learning_rate": 0.00014,
-      "loss": 1.1859,
+      "loss": 1.1822,
       "step": 9
     },
     {
       "epoch": 0.035842293906810034,
-      "grad_norm": 0.7875003218650818,
+      "grad_norm": 0.804837703704834,
       "learning_rate": 0.00016,
-      "loss": 1.1898,
+      "loss": 1.1865,
       "step": 10
     },
     {
       "epoch": 0.035842293906810034,
-      "eval_loss": 1.1698945760726929,
-      "eval_runtime": 8.6367,
-      "eval_samples_per_second": 54.419,
-      "eval_steps_per_second": 6.831,
+      "eval_loss": 1.1667453050613403,
+      "eval_runtime": 8.2688,
+      "eval_samples_per_second": 56.84,
+      "eval_steps_per_second": 7.135,
       "step": 10
     },
     {
       "epoch": 0.03942652329749104,
-      "grad_norm": 0.9833978414535522,
+      "grad_norm": 1.0118783712387085,
       "learning_rate": 0.00018,
-      "loss": 1.1755,
+      "loss": 1.1729,
       "step": 11
     },
     {
       "epoch": 0.043010752688172046,
-      "grad_norm": 0.890007734298706,
+      "grad_norm": 0.9140554070472717,
       "learning_rate": 0.0002,
-      "loss": 1.0835,
+      "loss": 1.0825,
       "step": 12
     },
     {
       "epoch": 0.04659498207885305,
-      "grad_norm": 0.9671109914779663,
+      "grad_norm": 0.9855129718780518,
       "learning_rate": 0.00019510565162951537,
-      "loss": 1.1763,
+      "loss": 1.1756,
       "step": 13
     },
     {
       "epoch": 0.05017921146953405,
-      "grad_norm": 0.7680312991142273,
+      "grad_norm": 0.7907399535179138,
       "learning_rate": 0.00018090169943749476,
-      "loss": 1.007,
+      "loss": 1.0081,
       "step": 14
     },
     {
       "epoch": 0.053763440860215055,
-      "grad_norm": 0.7991800308227539,
+      "grad_norm": 0.809781014919281,
       "learning_rate": 0.00015877852522924732,
-      "loss": 1.0003,
+      "loss": 0.9997,
       "step": 15
     },
     {
       "epoch": 0.053763440860215055,
-      "eval_loss": 1.107828140258789,
-      "eval_runtime": 8.6971,
-      "eval_samples_per_second": 54.041,
-      "eval_steps_per_second": 6.784,
+      "eval_loss": 1.1061427593231201,
+      "eval_runtime": 8.2438,
+      "eval_samples_per_second": 57.012,
+      "eval_steps_per_second": 7.157,
       "step": 15
+    },
+    {
+      "epoch": 0.05734767025089606,
+      "grad_norm": 0.6456992626190186,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9191,
+      "step": 16
+    },
+    {
+      "epoch": 0.06093189964157706,
+      "grad_norm": 0.9001843333244324,
+      "learning_rate": 0.0001,
+      "loss": 1.1871,
+      "step": 17
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 0.6480554342269897,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.0489,
+      "step": 18
+    },
+    {
+      "epoch": 0.06810035842293907,
+      "grad_norm": 0.7309454679489136,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.1242,
+      "step": 19
+    },
+    {
+      "epoch": 0.07168458781362007,
+      "grad_norm": 0.6513641476631165,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.077,
+      "step": 20
+    },
+    {
+      "epoch": 0.07168458781362007,
+      "eval_loss": 1.0755923986434937,
+      "eval_runtime": 8.336,
+      "eval_samples_per_second": 56.382,
+      "eval_steps_per_second": 7.078,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.250124588122112e+16,
+  "total_flos": 1.666832784162816e+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 sha256:8ad82ad32525e933af8b9fc0db6dec8e95c1d489a1adc2b0fa6be91ccfcf9268
+oid sha256:80e50aba904d39c5864e0f36c27d2c58f2cca1afdba552845d8b36d9735033ed
 size 6712