Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:102d34f3f27b40ee77ec12e016d974012f097b4b96ba45b8d940f87321cddd34
+oid sha256:119d868df08315ef6987d82547a57a18b88cd1b5b967646116fe1575cf91e1bc
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f534c3b16831353fa4b63569bc9a89294f70d374a11b77300960914fa249ce2
+oid sha256:7997d407d530053dc265970b89da31e783b48e60cf7d581555906a0d35844b5e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0019359210144226115,
+  "epoch": 0.003871842028845223,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 5.389,
       "eval_steps_per_second": 2.696,
       "step": 10
+    },
+    {
+      "epoch": 0.002129513115864873,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.002323105217307134,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.002516697318749395,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.9932,
+      "step": 13
+    },
+    {
+      "epoch": 0.002710289420191656,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.7767,
+      "step": 14
+    },
+    {
+      "epoch": 0.002903881521633917,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6115,
+      "step": 15
+    },
+    {
+      "epoch": 0.002903881521633917,
+      "eval_loss": NaN,
+      "eval_runtime": 404.0315,
+      "eval_samples_per_second": 5.383,
+      "eval_steps_per_second": 2.693,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030974736230761787,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.0032910657245184397,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.4516,
+      "step": 17
+    },
+    {
+      "epoch": 0.003484657825960701,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4837,
+      "step": 18
+    },
+    {
+      "epoch": 0.003678249927402962,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.003871842028845223,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.003871842028845223,
+      "eval_loss": NaN,
+      "eval_runtime": 403.0733,
+      "eval_samples_per_second": 5.396,
+      "eval_steps_per_second": 2.699,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -115,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -124,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3163091135102976.0,
+  "total_flos": 6408340481507328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null