Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "down_proj",
-    "o_proj",
     "up_proj",
     "v_proj",
+    "k_proj",
+    "gate_proj",
     "q_proj",
-    "k_proj"
+    "o_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 sha256:0a30597f32faaddfbef3b4dcae9bbe1abe1c69cba960004bcf3179a270710cfb
+oid sha256:022b760ec0373dda84699d50835126fd5a22dc94c96d33b3155939a634d9978c
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b412c55572ebab4610afe1221357e9e2d69053bc1bdb4cfcd44969ab5522f99
+oid sha256:6201ed75657655907ed9cc1e68d69f6dd3c6ac80152f50251b16b6a5947ae082
 size 63910

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000708842814105972,
+  "epoch": 0.0006379585326953748,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 7.08842814105972e-05,
-      "grad_norm": 0.05572463199496269,
+      "grad_norm": 0.05009423941373825,
       "learning_rate": 2e-05,
       "loss": 10.3888,
       "step": 1
@@ -18,97 +18,90 @@
     {
       "epoch": 7.08842814105972e-05,
       "eval_loss": 10.386297225952148,
-      "eval_runtime": 23.9211,
-      "eval_samples_per_second": 124.158,
-      "eval_steps_per_second": 124.158,
+      "eval_runtime": 27.7495,
+      "eval_samples_per_second": 107.029,
+      "eval_steps_per_second": 107.029,
       "step": 1
     },
     {
       "epoch": 0.0001417685628211944,
-      "grad_norm": 0.07294921576976776,
+      "grad_norm": 0.07014117389917374,
       "learning_rate": 4e-05,
       "loss": 10.3973,
       "step": 2
     },
     {
       "epoch": 0.0002126528442317916,
-      "grad_norm": 0.09582077711820602,
+      "grad_norm": 0.08233338594436646,
       "learning_rate": 6e-05,
       "loss": 10.3902,
       "step": 3
     },
     {
       "epoch": 0.0002126528442317916,
-      "eval_loss": 10.38620662689209,
-      "eval_runtime": 25.6376,
-      "eval_samples_per_second": 115.845,
-      "eval_steps_per_second": 115.845,
+      "eval_loss": 10.386211395263672,
+      "eval_runtime": 36.0589,
+      "eval_samples_per_second": 82.365,
+      "eval_steps_per_second": 82.365,
       "step": 3
     },
     {
       "epoch": 0.0002835371256423888,
-      "grad_norm": 0.07119490206241608,
+      "grad_norm": 0.06442844867706299,
       "learning_rate": 8e-05,
       "loss": 10.3829,
       "step": 4
     },
     {
       "epoch": 0.000354421407052986,
-      "grad_norm": 0.07462739944458008,
+      "grad_norm": 0.0734759271144867,
       "learning_rate": 0.0001,
       "loss": 10.3837,
       "step": 5
     },
     {
       "epoch": 0.0004253056884635832,
-      "grad_norm": 0.09681621193885803,
+      "grad_norm": 0.08815142512321472,
       "learning_rate": 0.00012,
       "loss": 10.3935,
       "step": 6
     },
     {
       "epoch": 0.0004253056884635832,
-      "eval_loss": 10.385847091674805,
-      "eval_runtime": 25.9218,
-      "eval_samples_per_second": 114.575,
-      "eval_steps_per_second": 114.575,
+      "eval_loss": 10.385868072509766,
+      "eval_runtime": 27.2276,
+      "eval_samples_per_second": 109.081,
+      "eval_steps_per_second": 109.081,
       "step": 6
     },
     {
       "epoch": 0.0004961899698741804,
-      "grad_norm": 0.07551346719264984,
+      "grad_norm": 0.06906867027282715,
       "learning_rate": 0.00014,
       "loss": 10.392,
       "step": 7
     },
     {
       "epoch": 0.0005670742512847776,
-      "grad_norm": 0.10659193247556686,
+      "grad_norm": 0.09693009406328201,
       "learning_rate": 0.00016,
-      "loss": 10.397,
+      "loss": 10.3971,
       "step": 8
     },
     {
       "epoch": 0.0006379585326953748,
-      "grad_norm": 0.09229987859725952,
+      "grad_norm": 0.07968022674322128,
       "learning_rate": 0.00018,
-      "loss": 10.3807,
+      "loss": 10.3808,
       "step": 9
     },
     {
       "epoch": 0.0006379585326953748,
-      "eval_loss": 10.385188102722168,
-      "eval_runtime": 27.1695,
-      "eval_samples_per_second": 109.314,
-      "eval_steps_per_second": 109.314,
+      "eval_loss": 10.38524055480957,
+      "eval_runtime": 23.5688,
+      "eval_samples_per_second": 126.014,
+      "eval_steps_per_second": 126.014,
       "step": 9
-    },
-    {
-      "epoch": 0.000708842814105972,
-      "grad_norm": 0.07869779318571091,
-      "learning_rate": 0.0002,
-      "loss": 10.382,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +116,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 139007262720.0,
+  "total_flos": 126076354560.0,
   "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:b6b787cf00a0bf21dcecfa64e4ed3fd7c145cc55e1992c0ed725bf3c55bad515
+oid sha256:bbcdbfa45fff0837fd8bd9e25494fc2d6f2c1706feeced80a01fede5c0e314c7
 size 6776