Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63921c571611449747545aeb024ecdafb7c574bddd8d5bd4c6c93cb03d42d3f1
+oid sha256:85dec33764f38007eddbee1398953bb2b83f7008c3297f41a003d25e5bf0f075
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcafb591a2e19b8e4db653081646b29e667507264640b8d151a2f9220b691622
+oid sha256:e293f4c582e30787ed63946f1bae5029fdb0d1758abb0cd7797943861f36e594
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ccbd9af6e0862437ca6945f3d1737d7c68b615082d9f5747986de5fe65273ba
+oid sha256:7e893e2196740ca9f6a9ece87f8ab844993dac7ee3013dd2d38ae88f0cef5aab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa8c8bbbef73e07545d01f97ae3d770537f54d16f7883e44e01bbac7a888fe6
+oid sha256:2c7c613ab0a392b081791cc42f29703de9195c096b1fb605709c10f8c6229c82
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c264a5c2f153cd1cb61d51c2cc869ec1d272328bb12c47ef502d0b94dfda2c9b
+oid sha256:531bb77ba50159216c327ace731444b2d30b9109473fe485b518b7f5fbb8d7bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2a8dfb0dbdaeed209b10a1ff0148c97d3e68c451ac406bc861778f52582b83
+oid sha256:cc32b2a9a068971413765631e2321c919c78429dad0a7ff3800cc34acac225ac
 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": 0.03288391976323578,
+  "epoch": 0.06576783952647156,
   "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": 33.075,
       "eval_steps_per_second": 4.139,
       "step": 25
+    },
+    {
+      "epoch": 0.03419927655376521,
+      "grad_norm": 3.8425331115722656,
+      "learning_rate": 5e-05,
+      "loss": 2.646,
+      "step": 26
+    },
+    {
+      "epoch": 0.03551463334429464,
+      "grad_norm": 3.500214099884033,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.5897,
+      "step": 27
+    },
+    {
+      "epoch": 0.03682999013482407,
+      "grad_norm": 2.8640339374542236,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.4347,
+      "step": 28
+    },
+    {
+      "epoch": 0.0381453469253535,
+      "grad_norm": 2.1953330039978027,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.3318,
+      "step": 29
+    },
+    {
+      "epoch": 0.039460703715882936,
+      "grad_norm": 1.360359787940979,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.3259,
+      "step": 30
+    },
+    {
+      "epoch": 0.040776060506412366,
+      "grad_norm": 1.5449228286743164,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1774,
+      "step": 31
+    },
+    {
+      "epoch": 0.0420914172969418,
+      "grad_norm": 1.6351491212844849,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1532,
+      "step": 32
+    },
+    {
+      "epoch": 0.04340677408747123,
+      "grad_norm": 2.0852408409118652,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.1224,
+      "step": 33
+    },
+    {
+      "epoch": 0.04472213087800066,
+      "grad_norm": 1.954745888710022,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1098,
+      "step": 34
+    },
+    {
+      "epoch": 0.04603748766853009,
+      "grad_norm": 1.9391647577285767,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.0364,
+      "step": 35
+    },
+    {
+      "epoch": 0.04735284445905952,
+      "grad_norm": 2.2001044750213623,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.91,
+      "step": 36
+    },
+    {
+      "epoch": 0.04866820124958895,
+      "grad_norm": 2.463000535964966,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.664,
+      "step": 37
+    },
+    {
+      "epoch": 0.049983558040118385,
+      "grad_norm": 1.6193251609802246,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3198,
+      "step": 38
+    },
+    {
+      "epoch": 0.051298914830647815,
+      "grad_norm": 1.781665563583374,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.4016,
+      "step": 39
+    },
+    {
+      "epoch": 0.052614271621177246,
+      "grad_norm": 1.9119794368743896,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2973,
+      "step": 40
+    },
+    {
+      "epoch": 0.053929628411706676,
+      "grad_norm": 1.837246060371399,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.2067,
+      "step": 41
+    },
+    {
+      "epoch": 0.055244985202236106,
+      "grad_norm": 1.520390510559082,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2404,
+      "step": 42
+    },
+    {
+      "epoch": 0.05656034199276554,
+      "grad_norm": 1.44670569896698,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.225,
+      "step": 43
+    },
+    {
+      "epoch": 0.05787569878329497,
+      "grad_norm": 1.3467217683792114,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1485,
+      "step": 44
+    },
+    {
+      "epoch": 0.0591910555738244,
+      "grad_norm": 1.2551240921020508,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0337,
+      "step": 45
+    },
+    {
+      "epoch": 0.060506412364353834,
+      "grad_norm": 1.223370909690857,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9589,
+      "step": 46
+    },
+    {
+      "epoch": 0.061821769154883265,
+      "grad_norm": 1.1751079559326172,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.0722,
+      "step": 47
+    },
+    {
+      "epoch": 0.0631371259454127,
+      "grad_norm": 1.4985276460647583,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.9858,
+      "step": 48
+    },
+    {
+      "epoch": 0.06445248273594212,
+      "grad_norm": 1.7056043148040771,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7523,
+      "step": 49
+    },
+    {
+      "epoch": 0.06576783952647156,
+      "grad_norm": 2.749437093734741,
+      "learning_rate": 0.0,
+      "loss": 1.7858,
+      "step": 50
+    },
+    {
+      "epoch": 0.06576783952647156,
+      "eval_loss": NaN,
+      "eval_runtime": 154.9001,
+      "eval_samples_per_second": 33.066,
+      "eval_steps_per_second": 4.138,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null