Training in progress, step 3500, checkpoint

last-checkpoint/adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "v_proj",
+    "up_proj",
+    "down_proj",
     "q_proj",
-    "o_proj",
     "k_proj",
-    "gate_proj"
+    "gate_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a6f9da203c188bdacd397a829a52964b4180a56e166306d8bbc54133988f0f
+oid sha256:ceab0d423864c65f625d7c8a95d0e7e0ca6f69af488ce695b76beeb8388ff40b
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e1f60306e90afba8d8ea21a94fb5b5bace2c271658c29b6481de1089c58e77
+oid sha256:5d9989976401ee46fea4f073a84e12c82976c25163631057b5e5a249eb3c3246
 size 72753027

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9105e32b09e0f9be21701a5869149a3c151b88c957b12bdcaa093d96fa1aa1c
+oid sha256:6e5fa56d82dcd7e85de7c8183937bc2faeaf12d4f27bad051b3c7a22134ed538
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc60ea0469cdd9ebf1d0a1679d7c13af12ce681298e1c2748b46362e30be0ab5
+oid sha256:5540a21525e4a32d214b1a9710461e5bc6329becf8733d38cdf637cfaaec0e56
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.626357528918523,
+  "epoch": 2.827600141435571,
   "eval_steps": 500,
-  "global_step": 3250,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2290,6 +2290,181 @@
       "learning_rate": 4.311756102502213e-06,
       "loss": 0.1199,
       "step": 3250
+    },
+    {
+      "epoch": 2.633631358286609,
+      "grad_norm": 8627.8505859375,
+      "learning_rate": 4.130868179710668e-06,
+      "loss": 0.1848,
+      "step": 3260
+    },
+    {
+      "epoch": 2.6417133909178157,
+      "grad_norm": 14247.7802734375,
+      "learning_rate": 3.953692777468876e-06,
+      "loss": 0.416,
+      "step": 3270
+    },
+    {
+      "epoch": 2.6497954235490226,
+      "grad_norm": 4759.4443359375,
+      "learning_rate": 3.7802442358634115e-06,
+      "loss": 0.3177,
+      "step": 3280
+    },
+    {
+      "epoch": 2.657877456180229,
+      "grad_norm": 4269.89892578125,
+      "learning_rate": 3.6105365933390754e-06,
+      "loss": 0.0936,
+      "step": 3290
+    },
+    {
+      "epoch": 2.665959488811436,
+      "grad_norm": 6439.9130859375,
+      "learning_rate": 3.4445835855626608e-06,
+      "loss": 0.1237,
+      "step": 3300
+    },
+    {
+      "epoch": 2.6740415214426427,
+      "grad_norm": 10297.259765625,
+      "learning_rate": 3.2823986443111854e-06,
+      "loss": 0.1953,
+      "step": 3310
+    },
+    {
+      "epoch": 2.6821235540738497,
+      "grad_norm": 15543.5859375,
+      "learning_rate": 3.1239948963848407e-06,
+      "loss": 0.4216,
+      "step": 3320
+    },
+    {
+      "epoch": 2.6902055867050563,
+      "grad_norm": 3996.56396484375,
+      "learning_rate": 2.9693851625444635e-06,
+      "loss": 0.3027,
+      "step": 3330
+    },
+    {
+      "epoch": 2.698287619336263,
+      "grad_norm": 4716.9501953125,
+      "learning_rate": 2.8185819564739037e-06,
+      "loss": 0.1063,
+      "step": 3340
+    },
+    {
+      "epoch": 2.70636965196747,
+      "grad_norm": 5304.83935546875,
+      "learning_rate": 2.671597483767191e-06,
+      "loss": 0.1064,
+      "step": 3350
+    },
+    {
+      "epoch": 2.714451684598677,
+      "grad_norm": 8085.703125,
+      "learning_rate": 2.528443640940653e-06,
+      "loss": 0.1923,
+      "step": 3360
+    },
+    {
+      "epoch": 2.7225337172298834,
+      "grad_norm": 16287.6484375,
+      "learning_rate": 2.38913201447003e-06,
+      "loss": 0.4251,
+      "step": 3370
+    },
+    {
+      "epoch": 2.73061574986109,
+      "grad_norm": 4544.6015625,
+      "learning_rate": 2.253673879852708e-06,
+      "loss": 0.3017,
+      "step": 3380
+    },
+    {
+      "epoch": 2.738697782492297,
+      "grad_norm": 4039.9560546875,
+      "learning_rate": 2.1220802006951203e-06,
+      "loss": 0.1068,
+      "step": 3390
+    },
+    {
+      "epoch": 2.7467798151235034,
+      "grad_norm": 5422.513671875,
+      "learning_rate": 1.994361627825364e-06,
+      "loss": 0.1124,
+      "step": 3400
+    },
+    {
+      "epoch": 2.7548618477547104,
+      "grad_norm": 10583.4833984375,
+      "learning_rate": 1.8705284984311677e-06,
+      "loss": 0.2164,
+      "step": 3410
+    },
+    {
+      "epoch": 2.762943880385917,
+      "grad_norm": 16692.498046875,
+      "learning_rate": 1.7505908352232037e-06,
+      "loss": 0.4409,
+      "step": 3420
+    },
+    {
+      "epoch": 2.771025913017124,
+      "grad_norm": 5393.38427734375,
+      "learning_rate": 1.634558345623921e-06,
+      "loss": 0.3108,
+      "step": 3430
+    },
+    {
+      "epoch": 2.7791079456483305,
+      "grad_norm": 5366.48095703125,
+      "learning_rate": 1.5224404209818076e-06,
+      "loss": 0.1037,
+      "step": 3440
+    },
+    {
+      "epoch": 2.787189978279537,
+      "grad_norm": 5171.4765625,
+      "learning_rate": 1.414246135811309e-06,
+      "loss": 0.1039,
+      "step": 3450
+    },
+    {
+      "epoch": 2.795272010910744,
+      "grad_norm": 9813.6513671875,
+      "learning_rate": 1.309984247058349e-06,
+      "loss": 0.1846,
+      "step": 3460
+    },
+    {
+      "epoch": 2.803354043541951,
+      "grad_norm": 15926.455078125,
+      "learning_rate": 1.2096631933915802e-06,
+      "loss": 0.4189,
+      "step": 3470
+    },
+    {
+      "epoch": 2.8114360761731576,
+      "grad_norm": 3362.9609375,
+      "learning_rate": 1.1132910945193698e-06,
+      "loss": 0.3116,
+      "step": 3480
+    },
+    {
+      "epoch": 2.819518108804364,
+      "grad_norm": 4051.453125,
+      "learning_rate": 1.0208757505326016e-06,
+      "loss": 0.1044,
+      "step": 3490
+    },
+    {
+      "epoch": 2.827600141435571,
+      "grad_norm": 5556.53857421875,
+      "learning_rate": 9.324246412733939e-07,
+      "loss": 0.1006,
+      "step": 3500
     }
   ],
   "logging_steps": 10,
@@ -2309,7 +2484,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.03516530319316e+17,
+  "total_flos": 4.34267192081452e+17,
   "train_batch_size": 4,
   "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:c48582cc9b2727d373cf81f576876ef5e4b0e3c9094657b869b98c824300773d
+oid sha256:baaa06e24635cf3973f697446cca6b46f255d47e1146983f25a8eecfcbdd11cb
 size 5841