Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d522b7d60479bce54fda9c72e40c6d259b78f46bcd5a7b6255713f2e7c246f
+oid sha256:05122fe79a6f6450703711ee059a2f97ada3f0b404ddfad95935f889b18da934
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5842c825deace1dbba7ae6366a25e9d5785e57254f8db360f7387d33a703e627
+oid sha256:e4ec516dace33211eda91969869fe056667229c2063e45c8ce0d4fb319c64b86
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d407d7fb865d97a3e5903d750f25e36d7fd02106c1ddef463fb40bacaac838
+oid sha256:1e821aa051e2f27695b75f642413adf41eda050a26ecfcd4c6eb36c2e4a03e03
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19df535c592fbfa76dd9045a97fd10d78e56b6418ffa3ad09fef22858923cdd0
+oid sha256:97e77db2f3bf54b4eaefe9c80b36e1202866bca1029f4413f1944896d443e596
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a878ba3cc1e1918275f475de6bc3f94722016a4895cb37421efb8c92e3ac86f
+oid sha256:7b939c27016c17ece1fa0ae67e72c692055bd5c6eb6f7db2b242110714178628
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3177ea4b394d20689f047a52c65a4c736ff1c10b2534d22548525087dc2bae5a
+oid sha256:69229c49401e88b3b3378c31d82dab5bb5c4af56b04c5c6fd06f1abbc7474757
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.694915254237288,
+  "epoch": 3.0508474576271185,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,146 @@
       "eval_samples_per_second": 17.493,
       "eval_steps_per_second": 4.548,
       "step": 25
+    },
+    {
+      "epoch": 1.7627118644067796,
+      "grad_norm": NaN,
+      "learning_rate": 4.682634170592537e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.8305084745762712,
+      "grad_norm": NaN,
+      "learning_rate": 4.3617997792374365e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.8983050847457628,
+      "grad_norm": NaN,
+      "learning_rate": 4.0470381785284936e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.9661016949152543,
+      "grad_norm": NaN,
+      "learning_rate": 3.7400287577942993e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.0338983050847457,
+      "grad_norm": NaN,
+      "learning_rate": 3.4424095451291274e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.1016949152542375,
+      "grad_norm": NaN,
+      "learning_rate": 3.155768467804314e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.169491525423729,
+      "grad_norm": NaN,
+      "learning_rate": 2.8816348799892133e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.23728813559322,
+      "grad_norm": NaN,
+      "learning_rate": 2.621471402984991e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.305084745762712,
+      "grad_norm": NaN,
+      "learning_rate": 2.3766661215071475e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.3728813559322033,
+      "grad_norm": NaN,
+      "learning_rate": 2.148525177652982e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.440677966101695,
+      "grad_norm": NaN,
+      "learning_rate": 1.938265802068357e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.5084745762711864,
+      "grad_norm": NaN,
+      "learning_rate": 1.74700981949555e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.576271186440678,
+      "grad_norm": NaN,
+      "learning_rate": 1.5757776633528655e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.6440677966101696,
+      "grad_norm": NaN,
+      "learning_rate": 1.4254829312808404e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": NaN,
+      "learning_rate": 1.2969275107035345e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.7796610169491527,
+      "grad_norm": NaN,
+      "learning_rate": 1.1907973004121738e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.847457627118644,
+      "grad_norm": NaN,
+      "learning_rate": 1.1076585509983283e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.915254237288136,
+      "grad_norm": NaN,
+      "learning_rate": 1.0479548436620041e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.983050847457627,
+      "grad_norm": NaN,
+      "learning_rate": 1.0120047235140178e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 3.0508474576271185,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -221,12 +361,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.652642132099072e+17,
+  "total_flos": 4.7747558377783296e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null