Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "v_proj",
     "q_proj",
     "down_proj",
-    "o_proj",
+    "k_proj",
     "gate_proj",
-    "v_proj",
-    "k_proj"
+    "o_proj",
+    "up_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 sha256:6c8e499cf79fa7c70e30a6b7238fbc5202b657a0e9452a27fceefebdbc2d6eba
+oid sha256:1f145eb880e6abdc5a9528bda50c50a86c5b3612191bbd9ba4d315b47b297469
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ffa7b70864738ce1964c47b68f69bea3421c65ca4ddc8389a40b1c27e420a5
+oid sha256:f86d20608c99dde831384d458f8274aa84f371ec02490f2bd0399469825c45f1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb48d936ef1e139b21187943d7515745a15ffcb66b2ac304ecbd8a84e592453
+oid sha256:5468253f7404473526345783a68536035f8790cb7d60b4a199ca22a538fb6e31
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb10f64a23de6be0a272874dbf4fd55d4242de66d0d67b71c2e67a96dbf1014
+oid sha256:c676d18cd3a8bd1516fedbbdb7ac08dc819faa0a3d565e8d0dda86138a3faf65
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fb447f9e0912c51aa1a856585ae1591673e4ceb6b3441be2655c1f5f1c493e
+oid sha256:b25fc9992080b267657e38e0e852722b8a94b9efa85ed128aeeed708987c3cbf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82291d34063ca349d0f4ec704bb56d6469972b7ed88cc07e0cd56b2a875a1c90
+oid sha256:e1529603aad62fddcf1c861e98f87c8b2d7d58b65b3e70d7baa62f67e62be32e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.4023845007451565,
+  "epoch": 1.2011922503725783,
   "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": 0.04769001490312966,
       "eval_loss": NaN,
-      "eval_runtime": 0.4901,
-      "eval_samples_per_second": 102.018,
-      "eval_steps_per_second": 26.525,
+      "eval_runtime": 0.5091,
+      "eval_samples_per_second": 98.215,
+      "eval_steps_per_second": 25.536,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 1.2011922503725783,
       "eval_loss": NaN,
-      "eval_runtime": 0.4905,
-      "eval_samples_per_second": 101.942,
-      "eval_steps_per_second": 26.505,
+      "eval_runtime": 0.5068,
+      "eval_samples_per_second": 98.657,
+      "eval_steps_per_second": 25.651,
       "step": 25
-    },
-    {
-      "epoch": 1.248882265275708,
-      "grad_norm": NaN,
-      "learning_rate": 7.11265577295385e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 1.2965722801788375,
-      "grad_norm": NaN,
-      "learning_rate": 6.890576474687263e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 1.3442622950819672,
-      "grad_norm": NaN,
-      "learning_rate": 6.664685702961344e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 1.391952309985097,
-      "grad_norm": NaN,
-      "learning_rate": 6.435602608679918e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 1.4396423248882266,
-      "grad_norm": NaN,
-      "learning_rate": 6.203955092681039e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 1.4873323397913563,
-      "grad_norm": NaN,
-      "learning_rate": 5.970378084704441e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 1.535022354694486,
-      "grad_norm": NaN,
-      "learning_rate": 5.735511803093249e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 1.5827123695976155,
-      "grad_norm": NaN,
-      "learning_rate": 5.500000000000001e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 1.6304023845007451,
-      "grad_norm": NaN,
-      "learning_rate": 5.264488196906753e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 1.6780923994038748,
-      "grad_norm": NaN,
-      "learning_rate": 5.0296219152955604e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 1.7257824143070044,
-      "grad_norm": NaN,
-      "learning_rate": 4.7960449073189606e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 1.773472429210134,
-      "grad_norm": NaN,
-      "learning_rate": 4.564397391320084e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 1.8211624441132637,
-      "grad_norm": NaN,
-      "learning_rate": 4.3353142970386564e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 1.8688524590163933,
-      "grad_norm": NaN,
-      "learning_rate": 4.109423525312738e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 1.9165424739195231,
-      "grad_norm": NaN,
-      "learning_rate": 3.887344227046149e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 1.9642324888226528,
-      "grad_norm": NaN,
-      "learning_rate": 3.6696851061589e-05,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 2.020864381520119,
-      "grad_norm": NaN,
-      "learning_rate": 3.45704275117204e-05,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 2.0685543964232487,
-      "grad_norm": NaN,
-      "learning_rate": 3.250000000000001e-05,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 2.1162444113263787,
-      "grad_norm": NaN,
-      "learning_rate": 3.0491243424323785e-05,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 2.1639344262295084,
-      "grad_norm": NaN,
-      "learning_rate": 2.854966364683872e-05,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 2.211624441132638,
-      "grad_norm": NaN,
-      "learning_rate": 2.6680582402757327e-05,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 2.2593144560357676,
-      "grad_norm": NaN,
-      "learning_rate": 2.4889122713851394e-05,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 2.3070044709388973,
-      "grad_norm": NaN,
-      "learning_rate": 2.3180194846605367e-05,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 2.354694485842027,
-      "grad_norm": NaN,
-      "learning_rate": 2.1558482853517257e-05,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 2.4023845007451565,
-      "grad_norm": NaN,
-      "learning_rate": 2.002843173443631e-05,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 2.4023845007451565,
-      "eval_loss": NaN,
-      "eval_runtime": 0.4895,
-      "eval_samples_per_second": 102.138,
-      "eval_steps_per_second": 26.556,
-      "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": 2.954393347424256e+16,
+  "total_flos": 1.477427377209344e+16,
   "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:e41cf186e68d86226a2fd879567d65612263bffc09ea253ebce47d1eb7612e59
+oid sha256:461b53c6caf291c27f4a987e9dafa2aef6f014faf67a010aa70d3e010eed8b6c
 size 6840