Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
-    "k_proj",
-    "o_proj",
-    "v_proj",
     "gate_proj",
-    "down_proj"
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_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 sha256:5cf92819c598c0f176d87f4df9c4e0c28e10ceafdf2b928e48456d66e8c369ee
+oid sha256:75562e3246a15d26b7654f8abe42110e9bb645beea72e7da02ed584dd6d51aa0
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427f3ece7ac4c36edb83baf2a9a99136c7ceee0fb07572549655f8b8f69fdcf6
+oid sha256:84d57923d4f6601e909a6a61907f19d993970dd0bc5e8269f940f88ebd451f0d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55fe47b3c81124410664ce023af9315362e9ccb8d49b1bc6029a2cfbba7b699
+oid sha256:f9fa56fefdd7944afe15e1ee2a1a2302b74936097ce9aaa24db16066a74d961d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229e535e54ce660e0733f9b959950557ce634b37fd79a57cdc6293c930a1b2cf
+oid sha256:135f9ca624cf27ad2a017f3c94d84a13ac778963ae3b7007dd254cf4eb41d14c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3839fa56ab666ffd6d8902ccacd5d052f39d56172682ec6b4cc27f8c496bd804
+oid sha256:91e3870a0ec43170468c743375292d503af5d5df91a982267d951fdd203c5217
 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": 0.0416579879191835,
+  "epoch": 0.02082899395959175,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,8 +18,8 @@
     {
       "epoch": 0.0008331597583836701,
       "eval_loss": NaN,
-      "eval_runtime": 4.986,
-      "eval_samples_per_second": 10.028,
+      "eval_runtime": 4.9868,
+      "eval_samples_per_second": 10.026,
       "eval_steps_per_second": 2.607,
       "step": 1
     },
@@ -194,193 +194,10 @@
     {
       "epoch": 0.02082899395959175,
       "eval_loss": NaN,
-      "eval_runtime": 3.8061,
-      "eval_samples_per_second": 13.137,
-      "eval_steps_per_second": 3.416,
+      "eval_runtime": 3.8068,
+      "eval_samples_per_second": 13.134,
+      "eval_steps_per_second": 3.415,
       "step": 25
-    },
-    {
-      "epoch": 0.021662153717975422,
-      "grad_norm": NaN,
-      "learning_rate": 5.500000000000001e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.02249531347635909,
-      "grad_norm": NaN,
-      "learning_rate": 5.205685918464356e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.023328473234742762,
-      "grad_norm": NaN,
-      "learning_rate": 4.912632135009769e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.02416163299312643,
-      "grad_norm": NaN,
-      "learning_rate": 4.6220935509274235e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.024994792751510102,
-      "grad_norm": NaN,
-      "learning_rate": 4.3353142970386564e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.02582795250989377,
-      "grad_norm": NaN,
-      "learning_rate": 4.053522406135775e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.026661112268277443,
-      "grad_norm": NaN,
-      "learning_rate": 3.777924554357096e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.02749427202666111,
-      "grad_norm": NaN,
-      "learning_rate": 3.509700894014496e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.028327431785044783,
-      "grad_norm": NaN,
-      "learning_rate": 3.250000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.02916059154342845,
-      "grad_norm": NaN,
-      "learning_rate": 2.9999339514117912e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.029993751301812123,
-      "grad_norm": NaN,
-      "learning_rate": 2.760573569460757e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.03082691106019579,
-      "grad_norm": NaN,
-      "learning_rate": 2.53294383204969e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.03166007081857946,
-      "grad_norm": NaN,
-      "learning_rate": 2.3180194846605367e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.032493230576963135,
-      "grad_norm": NaN,
-      "learning_rate": 2.1167208663446025e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.0333263903353468,
-      "grad_norm": NaN,
-      "learning_rate": 1.9299099686894423e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.03415955009373047,
-      "grad_norm": NaN,
-      "learning_rate": 1.758386744638546e-05,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.03499270985211414,
-      "grad_norm": NaN,
-      "learning_rate": 1.602885682970026e-05,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.035825869610497815,
-      "grad_norm": NaN,
-      "learning_rate": 1.464072663102903e-05,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.036659029368881484,
-      "grad_norm": NaN,
-      "learning_rate": 1.3425421036992098e-05,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.03749218912726515,
-      "grad_norm": NaN,
-      "learning_rate": 1.2388144172720251e-05,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.03832534888564882,
-      "grad_norm": NaN,
-      "learning_rate": 1.1533337816991932e-05,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.039158508644032496,
-      "grad_norm": NaN,
-      "learning_rate": 1.0864662381854632e-05,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.039991668402416164,
-      "grad_norm": NaN,
-      "learning_rate": 1.0384981238178534e-05,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.04082482816079983,
-      "grad_norm": NaN,
-      "learning_rate": 1.0096348454262845e-05,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.0416579879191835,
-      "grad_norm": NaN,
-      "learning_rate": 1e-05,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.0416579879191835,
-      "eval_loss": NaN,
-      "eval_runtime": 3.821,
-      "eval_samples_per_second": 13.085,
-      "eval_steps_per_second": 3.402,
-      "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": 5.840923519164088e+17,
+  "total_flos": 2.922230657969029e+17,
   "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 sha256:5af112a5c9071f33b9bcc53168d904691bfcec6e5f6d4c8752eea7eddb0d16e4
+oid sha256:ffd57b2e3902e8e91fd4da929e32eb58e1d51f9e07d6a4d4a25ea38bbf0b559c
 size 6840