Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032f6fd6198c274eb2d8ef8509afab13b016ca55cbc057b686cd62d92c5c612e
+oid sha256:680bd69aa0dadaf0f3f1447d094da01650c594790e155a9f9f0ec03fdc52213e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba1a444f499ea95174787b3457717cc3ddf9f825f5c77baf3d12d6e09eda142
+oid sha256:7744b059014d855acb80ce478371f68c54040207770ff7fa2274fd6079ada440
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d401e844b44692d1045aebf237cfc7d20000c6da1b72ab72c0056f5942de2e7
+oid sha256:9d5b86956307707c9ed1443a6bb28be859105a5257acd748001673e7fa7d740d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9f85cb9d017b9efef99cf13dfeb091e12eff1a920e930edc27d33bfe7703af
+oid sha256:7af8f60171843ed96483634a331f371a757301366eb4e58594de7cd5272b21cf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cea0a39e6b187e64a87ec8d1704de10ef570e34f36af1c6adcd492fc284d9b9
+oid sha256:59a6b586f98af3ff09fb73bf42a1738dff728671ee7137d99ac3d30b2e887483
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e81d03fc0f6d39d9d7eed67cbfd45f485166837aec97649b1fabcf6b30aab9f8
+oid sha256:b74deae522d20875b467a8a899a9297490d101c0a6919d4138784e2f1b61f906
 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": 0.03394433129667346,
+  "epoch": 0.06788866259334692,
   "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": 15.061,
       "eval_steps_per_second": 1.885,
       "step": 25
+    },
+    {
+      "epoch": 0.035302104548540394,
+      "grad_norm": 0.7135798931121826,
+      "learning_rate": 5e-05,
+      "loss": 0.006,
+      "step": 26
+    },
+    {
+      "epoch": 0.03665987780040733,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.03801765105227427,
+      "grad_norm": 0.0,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.03937542430414121,
+      "grad_norm": 0.0,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.04073319755600815,
+      "grad_norm": 0.0,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.042090970807875085,
+      "grad_norm": 0.0,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.04344874405974202,
+      "grad_norm": 0.0,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.04480651731160896,
+      "grad_norm": 0.0,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0461642905634759,
+      "grad_norm": 0.0,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.04752206381534284,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.048879837067209775,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.05023761031907671,
+      "grad_norm": 0.0,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.051595383570943655,
+      "grad_norm": 1.628795862197876,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0173,
+      "step": 38
+    },
+    {
+      "epoch": 0.05295315682281059,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.05431093007467753,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.055668703326544465,
+      "grad_norm": 0.0,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.05702647657841141,
+      "grad_norm": 0.0,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.058384249830278345,
+      "grad_norm": 0.0,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.05974202308214528,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.06109979633401222,
+      "grad_norm": 0.0,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.062457569585879155,
+      "grad_norm": 0.0,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.06381534283774609,
+      "grad_norm": 0.0,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.06517311608961303,
+      "grad_norm": 0.0,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.06653088934147998,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.06788866259334692,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.06788866259334692,
+      "eval_loss": NaN,
+      "eval_runtime": 174.5305,
+      "eval_samples_per_second": 28.431,
+      "eval_steps_per_second": 3.558,
+      "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