Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48e4a42d5b83281f75491c7b54216484f34e0a9099b433e9ea3709fa6f6bfee
+oid sha256:c79c881928c01183186d36cf8fc2b8a93d944f13824643ebc632285c19511fce
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44e5fe31937b4799c6231e0a3e3b3781ada07119ebe630a3e9db01020969c51
+oid sha256:f42bcc3d5a7780bbfdf2f3a2dd310533942cc1a7daba4bba71cc9190a8ff7a4f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd00ae53d2c311916d6881e828d7563797ceff6e8f0dba5d80b7181cd99478e
+oid sha256:906a4f9aaa923edcd0bbad58070787fdbfc7346cd0f27289b8ddbf4ad0b5b97b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0473852757a3424c0d03588c09be5f2f757192275683a837c9304ffa271ecf
+oid sha256:6b69a62ecbd94a05cce59e49c042d4f56fc143eb947140e6223d762628381d7b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c156b299f14def071dead23d3d7b85d49a1160c047c4f14ba262b44c50a54a51
+oid sha256:f77bb8910f4bad63417a2e9bc34997892faac8c1432df601758e94d40b0aa1cd
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.24301336573511542,
+  "epoch": 0.48602673147023084,
   "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": 68.136,
       "eval_steps_per_second": 17.715,
       "step": 25
+    },
+    {
+      "epoch": 0.25273390036452004,
+      "grad_norm": NaN,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.2624544349939247,
+      "grad_norm": NaN,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.27217496962332927,
+      "grad_norm": NaN,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.2818955042527339,
+      "grad_norm": NaN,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.2916160388821385,
+      "grad_norm": NaN,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.30133657351154314,
+      "grad_norm": NaN,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.3110571081409477,
+      "grad_norm": NaN,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.32077764277035237,
+      "grad_norm": NaN,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.330498177399757,
+      "grad_norm": NaN,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.3402187120291616,
+      "grad_norm": NaN,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.34993924665856624,
+      "grad_norm": NaN,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.3596597812879708,
+      "grad_norm": NaN,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.36938031591737547,
+      "grad_norm": NaN,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.37910085054678005,
+      "grad_norm": NaN,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.3888213851761847,
+      "grad_norm": NaN,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.3985419198055893,
+      "grad_norm": NaN,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.4082624544349939,
+      "grad_norm": NaN,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.41798298906439857,
+      "grad_norm": NaN,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.42770352369380316,
+      "grad_norm": NaN,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.4374240583232078,
+      "grad_norm": NaN,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.4471445929526124,
+      "grad_norm": NaN,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.456865127582017,
+      "grad_norm": NaN,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.4665856622114216,
+      "grad_norm": NaN,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.47630619684082626,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.48602673147023084,
+      "grad_norm": NaN,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.48602673147023084,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7493,
+      "eval_samples_per_second": 66.726,
+      "eval_steps_per_second": 17.349,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null