Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "down_proj",
-    "v_proj",
-    "k_proj",
     "gate_proj",
+    "q_proj",
+    "k_proj",
     "up_proj",
-    "o_proj"
+    "o_proj",
+    "v_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 sha256:3c6c3b49517918f71b5a8df86ce64802524c101812f6310fcee02fef5d317af6
+oid sha256:ecacf0120c3313aa6d110d54cdb0747ee47b71b2cd60beeadeed0c4feac79962
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053edfe2b776ed2cd6f5bb48484d2ab4fcc1017f1fbd99c25d7b9b51741e863a
+oid sha256:f821e79d65c8d0564b42993d068ec177b666bf0ef7c2f4543fe9bd904c61854f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ccf1cd3ade15fca6a0e6386eff1cae781e9532bb35fd78bb73d4976a6690b6
+oid sha256:181e8f33a3bf4e91ea544ce30914519460506a51257b90546721fc4efbff391e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b2dd61a83f9d0350bca1d58b5f4d9b1f56a177c83c5f711240c6563f7249ab
+oid sha256:26548f58a8165273e7515aa68dd8b85ac0101ba2962890b53aed479810e958a5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0461db364386b0a856446007042c6e9af833b164bff1a1d422fa237bc800ee3
+oid sha256:5d53af11e680c5cf10999d42795404bbc67d8bf5ad7f664289d3dfcc7302ade0
 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": 0.1983635011157947,
+  "epoch": 0.09918175055789735,
   "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": 0.003967270022315894,
       "eval_loss": NaN,
-      "eval_runtime": 93.3645,
-      "eval_samples_per_second": 18.197,
-      "eval_steps_per_second": 2.281,
+      "eval_runtime": 45.2456,
+      "eval_samples_per_second": 37.551,
+      "eval_steps_per_second": 4.708,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.09918175055789735,
       "eval_loss": NaN,
-      "eval_runtime": 93.5798,
-      "eval_samples_per_second": 18.156,
-      "eval_steps_per_second": 2.276,
+      "eval_runtime": 45.2235,
+      "eval_samples_per_second": 37.569,
+      "eval_steps_per_second": 4.71,
       "step": 25
-    },
-    {
-      "epoch": 0.10314902058021325,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.10711629060252914,
-      "grad_norm": NaN,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.11108356062484503,
-      "grad_norm": NaN,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.11505083064716093,
-      "grad_norm": NaN,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.11901810066947682,
-      "grad_norm": NaN,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.12298537069179272,
-      "grad_norm": NaN,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.1269526407141086,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.1309199107364245,
-      "grad_norm": NaN,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.1348871807587404,
-      "grad_norm": NaN,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.1388544507810563,
-      "grad_norm": NaN,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.1428217208033722,
-      "grad_norm": NaN,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.14678899082568808,
-      "grad_norm": NaN,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.15075626084800398,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.15472353087031987,
-      "grad_norm": NaN,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.15869080089263576,
-      "grad_norm": NaN,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.16265807091495166,
-      "grad_norm": NaN,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.16662534093726755,
-      "grad_norm": NaN,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.17059261095958345,
-      "grad_norm": NaN,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.17455988098189934,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.17852715100421523,
-      "grad_norm": NaN,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.18249442102653113,
-      "grad_norm": NaN,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.18646169104884702,
-      "grad_norm": NaN,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.19042896107116292,
-      "grad_norm": NaN,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.1943962310934788,
-      "grad_norm": NaN,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.1983635011157947,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.1983635011157947,
-      "eval_loss": NaN,
-      "eval_runtime": 93.2984,
-      "eval_samples_per_second": 18.21,
-      "eval_steps_per_second": 2.283,
-      "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": 5.658021338284032e+17,
+  "total_flos": 2.829010669142016e+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 sha256:676418cca0dc9378341f537cab319ea6c7b5ea904e5946c64ea3d363d78ed8a8
+oid sha256:9cf8cb9e35c54f1d6157963ebe4bb60c824db54a537c00e1ef67c68403edec46
 size 6776