Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11d06d8f3868ad429c79f49b94211b0b9b10a24c301fa09ba81a986705ccb1be
+oid sha256:486a790053cc12da3fd2c68af11a3c0e8e47e3a7ca6e56da3607c50abf220b80
 size 141633684

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f56979fdde627071c58efbd9c5ac3273699cb8d80179c714ffdb53f342a4c94
+oid sha256:aa2924b3546a7aefa8e79bd4f73a9fbfb1f40dedee33843a697ce5c82d677511
 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": 0.01418892554361321,
+  "epoch": 0.02837785108722642,
   "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": 12.923,
       "eval_steps_per_second": 6.462,
       "step": 100
+    },
+    {
+      "epoch": 0.01560781809797453,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.017026710652335852,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.01844560320669717,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.019864495761058493,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.021283388315419816,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.022702280869781134,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.024121173424142456,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.02554006597850378,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.026958958532865097,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.02837785108722642,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.02837785108722642,
+      "eval_loss": NaN,
+      "eval_runtime": 230.0619,
+      "eval_samples_per_second": 12.901,
+      "eval_steps_per_second": 6.45,
+      "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": 3775889670144000.0,
+  "total_flos": 7551779340288000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null