Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e94b00561eaad0db1c5b7d2c33b3ca421e679093fdb47868be832df928f2642
+oid sha256:a147378a7ed801e943956d1d7a8a9e90c49a117a24b9871ec5685e978df7b936
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32c0fb8f8079e7e79431159b4d10c4f159f30b6e1e5935a212d3085ea52dc2cf
+oid sha256:2a89fdcda2692559ba17c799230473ebd482aed6abeb800566826123aa243f2d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1b9bffa74df8b8aaf8a88ccf4a80620f24a48edc4305aa8220785bab1bebca
+oid sha256:a364b193cbdd708ae9772de0c09047581f513d43c08833983fa5a5fdd056ba94
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e30bf86bc4d26005b097270fbfd61c80e8e714c8b5317c6ae8a00b003b5ff29
+oid sha256:f94015853cf6641a3d7e31c2f051b8caa95ea0b4d5d046d4e72b2dc62f98aa0c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc76482bac54df5ea2133161de878ee70d4874ad37c886ed77508ddfd73cbb63
+oid sha256:272165c5380c6861e9310fc5483e0e222f1cef77995d41dd14d2b6c72e796843
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3b086c1791e1cbdc28b52ab920c23eeb4a54b27c7c17a045c5c26e70352283
+oid sha256:41b8a04c3118f68c0c83817b6ea659f1a05370c1e8ec0e3cc84f092947ccbe6a
 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": 0.08227067050596462,
+  "epoch": 0.16454134101192924,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 29.357,
       "eval_steps_per_second": 3.671,
       "step": 25
+    },
+    {
+      "epoch": 0.0855614973262032,
+      "grad_norm": 0.3497832715511322,
+      "learning_rate": 5e-05,
+      "loss": 1.4674,
+      "step": 26
+    },
+    {
+      "epoch": 0.0888523241464418,
+      "grad_norm": 0.3645464777946472,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4983,
+      "step": 27
+    },
+    {
+      "epoch": 0.09214315096668038,
+      "grad_norm": 0.38531163334846497,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4955,
+      "step": 28
+    },
+    {
+      "epoch": 0.09543397778691896,
+      "grad_norm": 0.38884270191192627,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4825,
+      "step": 29
+    },
+    {
+      "epoch": 0.09872480460715755,
+      "grad_norm": 0.3684292435646057,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4773,
+      "step": 30
+    },
+    {
+      "epoch": 0.10201563142739613,
+      "grad_norm": 0.3575262725353241,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4762,
+      "step": 31
+    },
+    {
+      "epoch": 0.10530645824763472,
+      "grad_norm": 0.381324827671051,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4799,
+      "step": 32
+    },
+    {
+      "epoch": 0.1085972850678733,
+      "grad_norm": 0.33787867426872253,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.48,
+      "step": 33
+    },
+    {
+      "epoch": 0.11188811188811189,
+      "grad_norm": 0.3649922013282776,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4888,
+      "step": 34
+    },
+    {
+      "epoch": 0.11517893870835047,
+      "grad_norm": 0.3968355357646942,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4914,
+      "step": 35
+    },
+    {
+      "epoch": 0.11846976552858905,
+      "grad_norm": 0.40086013078689575,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4862,
+      "step": 36
+    },
+    {
+      "epoch": 0.12176059234882765,
+      "grad_norm": 0.4988168179988861,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5299,
+      "step": 37
+    },
+    {
+      "epoch": 0.12505141916906623,
+      "grad_norm": 0.3682207465171814,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4489,
+      "step": 38
+    },
+    {
+      "epoch": 0.12834224598930483,
+      "grad_norm": 0.29406920075416565,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4104,
+      "step": 39
+    },
+    {
+      "epoch": 0.1316330728095434,
+      "grad_norm": 0.2865390479564667,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4344,
+      "step": 40
+    },
+    {
+      "epoch": 0.134923899629782,
+      "grad_norm": 0.25812751054763794,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4365,
+      "step": 41
+    },
+    {
+      "epoch": 0.13821472645002056,
+      "grad_norm": 0.2659599483013153,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4671,
+      "step": 42
+    },
+    {
+      "epoch": 0.14150555327025915,
+      "grad_norm": 0.2916855812072754,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.4769,
+      "step": 43
+    },
+    {
+      "epoch": 0.14479638009049775,
+      "grad_norm": 0.28812867403030396,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.417,
+      "step": 44
+    },
+    {
+      "epoch": 0.14808720691073632,
+      "grad_norm": 0.2936413288116455,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4749,
+      "step": 45
+    },
+    {
+      "epoch": 0.15137803373097491,
+      "grad_norm": 0.3101555407047272,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.4661,
+      "step": 46
+    },
+    {
+      "epoch": 0.15466886055121348,
+      "grad_norm": 0.32980605959892273,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.501,
+      "step": 47
+    },
+    {
+      "epoch": 0.15795968737145208,
+      "grad_norm": 0.3773946464061737,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4537,
+      "step": 48
+    },
+    {
+      "epoch": 0.16125051419169067,
+      "grad_norm": 0.4222414791584015,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.4935,
+      "step": 49
+    },
+    {
+      "epoch": 0.16454134101192924,
+      "grad_norm": 0.6277649402618408,
+      "learning_rate": 0.0,
+      "loss": 1.5493,
+      "step": 50
+    },
+    {
+      "epoch": 0.16454134101192924,
+      "eval_loss": NaN,
+      "eval_runtime": 69.9625,
+      "eval_samples_per_second": 29.259,
+      "eval_steps_per_second": 3.659,
+      "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": 3.127648818351309e+17,
+  "total_flos": 6.26462276232151e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null