Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "o_proj",
     "gate_proj",
     "v_proj",
     "down_proj",
-    "k_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj"
+    "up_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 sha256:5cf92819c598c0f176d87f4df9c4e0c28e10ceafdf2b928e48456d66e8c369ee
+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:d0c710e11ce1bd0c95a941121374a36c214ee6969a3cbf3f80b5762299329e7b
+oid sha256:943f1cee0c80a120d93ae1febde97b1dc489254b6f5d48c916cea2c31d57c289
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038183a2c683412f63c735bbae009fdff324216b194e871d5c2cf3457f5ebc17
+oid sha256:805f839a760fac1f6f1e8834dda437d54b2567573ad3566addc129813a788b7e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130f75510222ecadffdc20cce07314153cffcc80fbc714dffe819695e200ab1c
+oid sha256:a81b4c03a6198d5fb6f73c396fd5d19033706f9f78eed26cf4da304c37cf6824
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ecd78955323f91a29e2c43855d67554f9ec2c3fb56078eea9e3709891cdb19
+oid sha256:b248337758cc4fcd55dff580e18d91b50c516bd89b8524d031a59fe958fdbffb
 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": 0.09765625,
+  "epoch": 0.048828125,
   "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": 0.001953125,
       "eval_loss": NaN,
-      "eval_runtime": 2.4183,
-      "eval_samples_per_second": 20.675,
-      "eval_steps_per_second": 5.376,
+      "eval_runtime": 2.4217,
+      "eval_samples_per_second": 20.647,
+      "eval_steps_per_second": 5.368,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.048828125,
       "eval_loss": NaN,
-      "eval_runtime": 1.7831,
-      "eval_samples_per_second": 28.041,
-      "eval_steps_per_second": 7.291,
+      "eval_runtime": 1.7911,
+      "eval_samples_per_second": 27.916,
+      "eval_steps_per_second": 7.258,
       "step": 25
-    },
-    {
-      "epoch": 0.05078125,
-      "grad_norm": NaN,
-      "learning_rate": 5.500000000000001e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.052734375,
-      "grad_norm": NaN,
-      "learning_rate": 5.205685918464356e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.0546875,
-      "grad_norm": NaN,
-      "learning_rate": 4.912632135009769e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.056640625,
-      "grad_norm": NaN,
-      "learning_rate": 4.6220935509274235e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.05859375,
-      "grad_norm": NaN,
-      "learning_rate": 4.3353142970386564e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.060546875,
-      "grad_norm": NaN,
-      "learning_rate": 4.053522406135775e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.0625,
-      "grad_norm": NaN,
-      "learning_rate": 3.777924554357096e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.064453125,
-      "grad_norm": NaN,
-      "learning_rate": 3.509700894014496e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.06640625,
-      "grad_norm": NaN,
-      "learning_rate": 3.250000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.068359375,
-      "grad_norm": NaN,
-      "learning_rate": 2.9999339514117912e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.0703125,
-      "grad_norm": NaN,
-      "learning_rate": 2.760573569460757e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.072265625,
-      "grad_norm": NaN,
-      "learning_rate": 2.53294383204969e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.07421875,
-      "grad_norm": NaN,
-      "learning_rate": 2.3180194846605367e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.076171875,
-      "grad_norm": NaN,
-      "learning_rate": 2.1167208663446025e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.078125,
-      "grad_norm": NaN,
-      "learning_rate": 1.9299099686894423e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.080078125,
-      "grad_norm": NaN,
-      "learning_rate": 1.758386744638546e-05,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.08203125,
-      "grad_norm": NaN,
-      "learning_rate": 1.602885682970026e-05,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.083984375,
-      "grad_norm": NaN,
-      "learning_rate": 1.464072663102903e-05,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.0859375,
-      "grad_norm": NaN,
-      "learning_rate": 1.3425421036992098e-05,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.087890625,
-      "grad_norm": NaN,
-      "learning_rate": 1.2388144172720251e-05,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.08984375,
-      "grad_norm": NaN,
-      "learning_rate": 1.1533337816991932e-05,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.091796875,
-      "grad_norm": NaN,
-      "learning_rate": 1.0864662381854632e-05,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.09375,
-      "grad_norm": NaN,
-      "learning_rate": 1.0384981238178534e-05,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.095703125,
-      "grad_norm": NaN,
-      "learning_rate": 1.0096348454262845e-05,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.09765625,
-      "grad_norm": NaN,
-      "learning_rate": 1e-05,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.09765625,
-      "eval_loss": NaN,
-      "eval_runtime": 1.7766,
-      "eval_samples_per_second": 28.144,
-      "eval_steps_per_second": 7.317,
-      "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": 5.658027780734976e+17,
+  "total_flos": 2.829013890367488e+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:c0ea2fd2e46c7cdca392eab5976797e53ec4f6571917ef6562e56d69db781b4d
+oid sha256:0aaf6d279bc69c270c39899d89fbc5854ec4ef81c9ab01e4296c4801e34228fa
 size 6840