Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3e24d08a94f56c8824d84e19cb6deee9cb5155eb4d32ab05b9be806f250004
+oid sha256:c4209963bfa5ac58f035f88dc2e74ddf5435f1c25dcfb82807df94356008e3be
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41d4e80c706e088832777687c1462f6f58df50c55b780be92c7c21c964ae6700
+oid sha256:db3a9b853bfa63265641d1a800a676f95997f669815401bdef39edcb5405f158
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec7d4a80e02b10bc12c2e699195e98c405b9430b961e6239196cbbd7dd44a14
+oid sha256:98d6f21c9ba1db10e34c6e49541fc7696c10131dc92bc1b76d6324bc4d43ce6a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f09e67607192f9e63ebb702ef9622f89173d463f05a66e192c9ec873da5df1f
+oid sha256:47c11888e37a5651e2fcae5c81f8a655f14442e6c785436e791bcfbb5c8a8e4e
 size 15024

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07089684509039348,
+  "epoch": 0.14179369018078697,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.002835873803615739,
       "eval_loss": NaN,
-      "eval_runtime": 130.4225,
-      "eval_samples_per_second": 18.218,
-      "eval_steps_per_second": 2.277,
+      "eval_runtime": 63.135,
+      "eval_samples_per_second": 37.634,
+      "eval_steps_per_second": 4.704,
       "step": 1
     },
     {
@@ -194,10 +194,193 @@
     {
       "epoch": 0.07089684509039348,
       "eval_loss": NaN,
-      "eval_runtime": 130.0655,
-      "eval_samples_per_second": 18.268,
-      "eval_steps_per_second": 2.283,
+      "eval_runtime": 63.1924,
+      "eval_samples_per_second": 37.599,
+      "eval_steps_per_second": 4.7,
       "step": 25
+    },
+    {
+      "epoch": 0.07373271889400922,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.07656859269762496,
+      "grad_norm": NaN,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0794044665012407,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.08224034030485644,
+      "grad_norm": NaN,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.08507621410847217,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": NaN,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.09074796171570365,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.0935838355193194,
+      "grad_norm": NaN,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.09641970932293513,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.09925558312655088,
+      "grad_norm": NaN,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.10209145693016661,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.10492733073378235,
+      "grad_norm": NaN,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.10776320453739809,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.11059907834101383,
+      "grad_norm": NaN,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.11343495214462956,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.11627082594824531,
+      "grad_norm": NaN,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.11910669975186104,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.12194257355547679,
+      "grad_norm": NaN,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.12477844735909252,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.12761432116270827,
+      "grad_norm": NaN,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.130450194966324,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.13328606876993973,
+      "grad_norm": NaN,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.13612194257355548,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.13895781637717122,
+      "grad_norm": NaN,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.14179369018078697,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.14179369018078697,
+      "eval_loss": NaN,
+      "eval_runtime": 63.2017,
+      "eval_samples_per_second": 37.594,
+      "eval_steps_per_second": 4.699,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.829062208749568e+17,
+  "total_flos": 5.658124417499136e+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 sha256:71bebcc0519cae1e60b4d19cf548f5635e381b6f19a5338cc9ecce64ea4992a8
+oid sha256:8ac664eb1c9fe3625f8202cbe118cbd78f25204fa44f2e29aa3ab1311d169ffe
 size 6776