Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "k_proj",
     "q_proj",
-    "up_proj",
-    "gate_proj",
     "o_proj",
-    "k_proj",
     "v_proj",
-    "down_proj"
+    "up_proj",
+    "gate_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 sha256:9cd5b5d1a73f9b8e6baec8a928a4f2817655f0734c630bf4dc081958eed3d292
+oid sha256:a1bb923180bf906f61567f6ffa0199a0bf834d04b7ab41a1e291b49dcf47bc41
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d63b5ad8a9d0c44b13189a4a0fff26a4a62f7ae4474aaf3af256f5f48d1bb27e
+oid sha256:6dc5d04835b9294c660508c05ef693ae5c1a2982a1f2c9b780935f977957545f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb67b36310535c409328678ac50770f9e35146c235f7adc9417e22cb84e26aa3
+oid sha256:b8f02b34da6e1b56b8f52f051763413d771d26074b1f6d5bb37493d4a36e0a15
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b62bfe5766a7eba012d624d7e2b70be6ff307766ae8ce65e5a7c60ca9d6a64
+oid sha256:faede547f91fd2d9301fc30bf98a11e40f75afe37d2cd36a86cb12bdfd3c6bc4
 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": 2.2028,
-      "eval_samples_per_second": 22.699,
-      "eval_steps_per_second": 5.902,
+      "eval_runtime": 2.2206,
+      "eval_samples_per_second": 22.517,
+      "eval_steps_per_second": 5.854,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.062315002336812586,
       "eval_loss": NaN,
-      "eval_runtime": 1.7018,
-      "eval_samples_per_second": 29.381,
-      "eval_steps_per_second": 7.639,
+      "eval_runtime": 1.6705,
+      "eval_samples_per_second": 29.931,
+      "eval_steps_per_second": 7.782,
       "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": 0.7884,
-      "eval_samples_per_second": 63.417,
-      "eval_steps_per_second": 16.488,
-      "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:b012780124878add871a5aa22592c067c6495898c7bcd5f7d2598aa3dcc442b7
+oid sha256:5522e2c7db155cd6c11afc672d2af988c63960d700791d6bfddaa4ab197d3096
 size 6840