Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45fab6ec531c5ad4d6c2449611c53cc4ce63abf73aba68c717b54d6718b36c7
+oid sha256:016e9a66ad22ecff006d4e1976b360d119fe10ea355a08352998f327634458e8
 size 650152596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d27cfdd81fa620304c36c1cb2f0f2ccfbe389eef67a15d318b5c0a6f30cc074
+oid sha256:0a3b427fec24d1bc1e54c4ce733cad877dd9651f49f35c11188643091da3a68c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691263e55c7bb34b6e090bd89cf079f362100d7bd758be475bd3e7091c1a4ed6
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.00521097953387788,
+  "epoch": 0.01042195906775576,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 2.675,
       "eval_steps_per_second": 1.338,
       "step": 100
+    },
+    {
+      "epoch": 0.005732077487265669,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.006253175440653457,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.006774273394041245,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.007295371347429033,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.00781646930081682,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.00833756725420461,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.008858665207592396,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.009379763160980185,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.009900861114367974,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.01042195906775576,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.01042195906775576,
+      "eval_loss": NaN,
+      "eval_runtime": 3022.215,
+      "eval_samples_per_second": 2.674,
+      "eval_steps_per_second": 1.337,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -107,7 +185,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.713123940800922e+16,
+  "total_flos": 1.5596515518264115e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null