Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd2bda8e8bc890f50fda08843cee4299a0f1710fc6e4186ee1d09b41eb7f6c9
+oid sha256:3290e1bfdb821fc505bb613bd34d21bdc0671d22f099e1807755f4b92e6605e3
 size 1204200

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e9e2d5ff9e656d4067e91cef6dc7619fb9c97b8cf57667ba4f3d1df752ad96
+oid sha256:24631e3c3fcd6b149f3c47fb6dfd622e77d1273fe38aa5d7d06195aad3953353
 size 2558458

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec1da74034970cc0d4e3edb275031027deae5910f81195bcf55318ec21dc95c2
+oid sha256:08d7676b5d1a4b82513861977dc0a736e6de7f72b4140da1f1530b85cf59472e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f09f7dad4117a7dba14d35382ed7c032b249c387c74979ff0ec91d65e52e7cc
+oid sha256:40c859f3005f7a1f463d753ca22d207b6cc4d2906704f3f2087aead727288d8b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc059cc6828033bc816960a3bdae048e5edccd7392380b64a3789817a69acc2
+oid sha256:011ca504c7d8a4ecec31ca8819a4ab4ef32fdb8b111fd01637d27d87256ae6b3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b4eb93747b7ec7a0e4e7b828ec936426746ed114cc6e9614e32d22ce8209c4
+oid sha256:08cece9d42d1ebcbfff98d6738d4f79c725d2cebbde4df2a254fb34c92413ad4
 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": 0.01473676454334451,
+  "epoch": 0.02947352908668902,
   "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": 70.214,
       "eval_steps_per_second": 8.779,
       "step": 25
+    },
+    {
+      "epoch": 0.015326235125078289,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.01591570570681207,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.01650517628854585,
+      "grad_norm": 0.0,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.01709464687027963,
+      "grad_norm": 0.0,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.017684117452013412,
+      "grad_norm": 0.0,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.01827358803374719,
+      "grad_norm": 0.0,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.01886305861548097,
+      "grad_norm": 0.0,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.01945252919721475,
+      "grad_norm": 0.0,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.020041999778948532,
+      "grad_norm": 0.0,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.020631470360682313,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.021220940942416094,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.021810411524149875,
+      "grad_norm": 0.0,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.022399882105883652,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.022989352687617433,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.023578823269351214,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.024168293851084995,
+      "grad_norm": 0.0,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.024757764432818775,
+      "grad_norm": 0.0,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.025347235014552556,
+      "grad_norm": 0.0,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.025936705596286334,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.026526176178020115,
+      "grad_norm": 0.0,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.027115646759753895,
+      "grad_norm": 0.0,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.027705117341487676,
+      "grad_norm": 0.0,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.028294587923221457,
+      "grad_norm": 0.0,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.028884058504955238,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.02947352908668902,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.02947352908668902,
+      "eval_loss": NaN,
+      "eval_runtime": 162.6812,
+      "eval_samples_per_second": 70.254,
+      "eval_steps_per_second": 8.784,
+      "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": 208867531161600.0,
+  "total_flos": 417735062323200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null