Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
-    "down_proj",
     "gate_proj",
     "k_proj",
+    "o_proj",
+    "down_proj",
     "up_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:071b70566aca84b08154b7a35c97f6f94250816dc6cd334c56689333a2231e16
+oid sha256:515df41aa989f57bf5ca361ba1f48add84b2fdaf3d71bbf2a3ff588d5a524938
 size 139313234

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d69cb66ebc260d8869efbb5ba5dbb658414a02614c53ac9ffabd1237f1298c4
+oid sha256:77ba60a10c45dc14c4d12bd50ce500bb024a45ec7aa99355903f76f2687aa489
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b8aa78776a3dab5938d269ec2dabb8fe56792ac8910da57598cd3925d55f156
+oid sha256:035d30d3596affb585c420263eeb31c4306665687cb2e080003e59ad07b5fc45
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892466f031a452e3606086e69968168fe2222bd81990cca78883f7662c7db650
+oid sha256:984e5a5dd0d9f2659cb5298e28a06644e5d79b6871750fa1f3764e6d6807f62c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25117e89b1035e7b8bf425d162f67c6535d863f5428d1fde8ddce13d9ee1cbca
+oid sha256:ea61ce0bfe3af212163cca699b0991e12364e4c2ebb7a417f75069735381c034
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
+oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12463000467362517,
+  "epoch": 0.062315002336812586,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0024926000934725034,
       "eval_loss": NaN,
-      "eval_runtime": 2.6103,
-      "eval_samples_per_second": 19.155,
-      "eval_steps_per_second": 4.98,
+      "eval_runtime": 2.6059,
+      "eval_samples_per_second": 19.187,
+      "eval_steps_per_second": 4.989,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.062315002336812586,
       "eval_loss": NaN,
-      "eval_runtime": 1.9812,
-      "eval_samples_per_second": 25.237,
-      "eval_steps_per_second": 6.562,
+      "eval_runtime": 2.0189,
+      "eval_samples_per_second": 24.766,
+      "eval_steps_per_second": 6.439,
       "step": 25
-    },
-    {
-      "epoch": 0.06480760243028509,
-      "grad_norm": NaN,
-      "learning_rate": 5.500000000000001e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.0673002025237576,
-      "grad_norm": NaN,
-      "learning_rate": 5.205685918464356e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.0697928026172301,
-      "grad_norm": NaN,
-      "learning_rate": 4.912632135009769e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.0722854027107026,
-      "grad_norm": NaN,
-      "learning_rate": 4.6220935509274235e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.07477800280417511,
-      "grad_norm": NaN,
-      "learning_rate": 4.3353142970386564e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.0772706028976476,
-      "grad_norm": NaN,
-      "learning_rate": 4.053522406135775e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.07976320299112011,
-      "grad_norm": NaN,
-      "learning_rate": 3.777924554357096e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.08225580308459261,
-      "grad_norm": NaN,
-      "learning_rate": 3.509700894014496e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.08474840317806512,
-      "grad_norm": NaN,
-      "learning_rate": 3.250000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.08724100327153762,
-      "grad_norm": NaN,
-      "learning_rate": 2.9999339514117912e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.08973360336501013,
-      "grad_norm": NaN,
-      "learning_rate": 2.760573569460757e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.09222620345848263,
-      "grad_norm": NaN,
-      "learning_rate": 2.53294383204969e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.09471880355195514,
-      "grad_norm": NaN,
-      "learning_rate": 2.3180194846605367e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.09721140364542763,
-      "grad_norm": NaN,
-      "learning_rate": 2.1167208663446025e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.09970400373890013,
-      "grad_norm": NaN,
-      "learning_rate": 1.9299099686894423e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.10219660383237264,
-      "grad_norm": NaN,
-      "learning_rate": 1.758386744638546e-05,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.10468920392584515,
-      "grad_norm": NaN,
-      "learning_rate": 1.602885682970026e-05,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.10718180401931765,
-      "grad_norm": NaN,
-      "learning_rate": 1.464072663102903e-05,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.10967440411279016,
-      "grad_norm": NaN,
-      "learning_rate": 1.3425421036992098e-05,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.11216700420626266,
-      "grad_norm": NaN,
-      "learning_rate": 1.2388144172720251e-05,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.11465960429973517,
-      "grad_norm": NaN,
-      "learning_rate": 1.1533337816991932e-05,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.11715220439320767,
-      "grad_norm": NaN,
-      "learning_rate": 1.0864662381854632e-05,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.11964480448668016,
-      "grad_norm": NaN,
-      "learning_rate": 1.0384981238178534e-05,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.12213740458015267,
-      "grad_norm": NaN,
-      "learning_rate": 1.0096348454262845e-05,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.12463000467362517,
-      "grad_norm": NaN,
-      "learning_rate": 1e-05,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.12463000467362517,
-      "eval_loss": NaN,
-      "eval_runtime": 1.0208,
-      "eval_samples_per_second": 48.981,
-      "eval_steps_per_second": 12.735,
-      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -395,7 +212,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -404,12 +221,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.637081579670733e+16,
+  "total_flos": 1.32098857893888e+16,
   "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:b5d376f131ce3c8acd1ee15f6a6bd8a325117b7350837c9a4fafe7e80cfccd0e
+oid sha256:332481211f5a5fa37a04b7097dc28a188770f4264716bb3591ecd58f79715865
 size 6840