Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e20d855196b0a5a431111879825930a8e746bb641dd1b50692b4f968a5832b9
+oid sha256:e1917a5f8509c6216baa4a40f973c6f6a86736ec9be48b45620bd082c3d6b658
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd1ee46340ee5bc365cdd8e8716bcbcdecd536cc8b44c082bb140f5159df1c2
+oid sha256:ade0b1544b5432c02c629d743fcfdb104c6c039b58276ba96722337f91758e18
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ec02fc020a8dc3173476948a5972558632fd7f8145991e11796687a635438c
+oid sha256:5fe3e63930b8f3bbcbc65ef05cd960fbe9a6793804ab1f6b32e249c22b8bdec5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3ffc4751ccee63eb5814ee9fc5d0c62c3843530dd693aa726d5333388ec100
+oid sha256:361a04de78da44c0421afe441cfa1c0736559d80fa2b0f44201a7fa64e44d7dd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49333ad16370f882a50e13520d9f84cb79df30a9373911b25f37f0dbf61822c0
+oid sha256:7dedc7be3b013ddf4e3c45e5cbd97fd6a196faa7ced4f5291a3ee7d202310a2b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
+oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.026308000920780034,
+  "epoch": 0.05261600184156007,
   "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": 33.371,
       "eval_steps_per_second": 8.676,
       "step": 25
+    },
+    {
+      "epoch": 0.027360320957611234,
+      "grad_norm": NaN,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.028412640994442434,
+      "grad_norm": NaN,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.029464961031273638,
+      "grad_norm": NaN,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.030517281068104838,
+      "grad_norm": NaN,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.03156960110493604,
+      "grad_norm": NaN,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03262192114176724,
+      "grad_norm": NaN,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03367424117859844,
+      "grad_norm": NaN,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.03472656121542964,
+      "grad_norm": NaN,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.03577888125226084,
+      "grad_norm": NaN,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.03683120128909204,
+      "grad_norm": NaN,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.03788352132592324,
+      "grad_norm": NaN,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.03893584136275445,
+      "grad_norm": NaN,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.03998816139958565,
+      "grad_norm": NaN,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.04104048143641685,
+      "grad_norm": NaN,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.04209280147324805,
+      "grad_norm": NaN,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04314512151007925,
+      "grad_norm": NaN,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.04419744154691045,
+      "grad_norm": NaN,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.04524976158374166,
+      "grad_norm": NaN,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.04630208162057286,
+      "grad_norm": NaN,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.04735440165740406,
+      "grad_norm": NaN,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04840672169423526,
+      "grad_norm": NaN,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.04945904173106646,
+      "grad_norm": NaN,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.05051136176789766,
+      "grad_norm": NaN,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.05156368180472886,
+      "grad_norm": NaN,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.05261600184156007,
+      "grad_norm": NaN,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.05261600184156007,
+      "eval_loss": NaN,
+      "eval_runtime": 3.304,
+      "eval_samples_per_second": 15.133,
+      "eval_steps_per_second": 3.935,
+      "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": 2.652642132099072e+17,
+  "total_flos": 5.305284264198144e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null