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",
-    "o_proj",
+    "gate_proj",
     "k_proj",
+    "o_proj",
+    "v_proj",
     "down_proj",
-    "gate_proj",
-    "v_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 sha256:35c3d917c3253743e3698a5a508a9d126be2f1e32bdc7dac1045cb54e8f984b5
+oid sha256:60661d2d2583d4765a71aa4fe25b1abf5edc35f7fe00c95c81e579fbaca57ea4
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45a91944b9ed7872669329f59b6d64a3067181f36994ae7ad2ec8a5f6da4c24
+oid sha256:0bb5bb0220636d61af5ad9be8c5843279841b8a97ad5cc4769610a9d9bf84af0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03215c9d3430f648c58d3f3f89d4318d4ea8dfd50e43ac9bbd114566c9349088
+oid sha256:e1f748a07528ede82670a20a1fe75f20a1777514422b5b43f73cd3b048a638b6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c929e34d8c4f70cea0da428cbb8bc8ed6bd3a3a90f5cb6753cf54fc227c19e12
+oid sha256:690a95c25378996cb2ec082a9c891f247d4e91caa1274018190c6374eef1738a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523da879df78cc0258b83c4e5007b0fd44e2a2fe0018a7a243f09f442bcb950f
+oid sha256:57263176d89ea862740a9516dddd399dd75e8f2d0855204dbf159d6961b0e7bb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011782900066278813,
+  "epoch": 0.0058914500331394065,
   "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": 0.00023565800132557626,
       "eval_loss": NaN,
-      "eval_runtime": 354.7638,
-      "eval_samples_per_second": 80.583,
-      "eval_steps_per_second": 10.074,
+      "eval_runtime": 353.7873,
+      "eval_samples_per_second": 80.806,
+      "eval_steps_per_second": 10.102,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.0058914500331394065,
       "eval_loss": NaN,
-      "eval_runtime": 352.8488,
-      "eval_samples_per_second": 81.021,
-      "eval_steps_per_second": 10.129,
+      "eval_runtime": 352.6462,
+      "eval_samples_per_second": 81.067,
+      "eval_steps_per_second": 10.135,
       "step": 25
-    },
-    {
-      "epoch": 0.006127108034464983,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.006362766035790559,
-      "grad_norm": NaN,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.006598424037116135,
-      "grad_norm": NaN,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.006834082038441712,
-      "grad_norm": NaN,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.007069740039767288,
-      "grad_norm": NaN,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.007305398041092864,
-      "grad_norm": NaN,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.00754105604241844,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.007776714043744017,
-      "grad_norm": NaN,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.008012372045069592,
-      "grad_norm": NaN,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.008248030046395169,
-      "grad_norm": NaN,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.008483688047720745,
-      "grad_norm": NaN,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.008719346049046322,
-      "grad_norm": NaN,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.008955004050371898,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.009190662051697473,
-      "grad_norm": NaN,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.00942632005302305,
-      "grad_norm": NaN,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.009661978054348626,
-      "grad_norm": NaN,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.009897636055674203,
-      "grad_norm": NaN,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.01013329405699978,
-      "grad_norm": NaN,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.010368952058325356,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.010604610059650932,
-      "grad_norm": NaN,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.010840268060976509,
-      "grad_norm": NaN,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.011075926062302083,
-      "grad_norm": NaN,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.01131158406362766,
-      "grad_norm": NaN,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.011547242064953236,
-      "grad_norm": NaN,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.011782900066278813,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.011782900066278813,
-      "eval_loss": NaN,
-      "eval_runtime": 354.0922,
-      "eval_samples_per_second": 80.736,
-      "eval_steps_per_second": 10.093,
-      "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": 1.1131753884286976e+17,
+  "total_flos": 5.585743266394931e+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:fdb6386fcfb6c5cab20d117558830e388e799ea5767e106b960d68906a66ce80
+oid sha256:601e24b56f548e6cc98b8d3e5be94cbe1d69d53bb9c51045dbb8c835059d4c9e
 size 6776