Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a51445d3fa122f1ee7119941e8fbc5fbbf82d0285b0ebb1a3c0d7635ca12f5
+oid sha256:9c5ac0b429a93f50fe51370c47a5d8df922ae4b55b39faffc2c7587e8e0f8b6b
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8e63f350191539b489fdfa8c98b48673fb089fe658d66458a7088b1e4ef7ad
+oid sha256:97f17f928f8a402cb6d7a73e49874eee9fcf5cdab22b1c73d6ca074c3278ef8f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef42f1c0311c3136e7086fe40f599adb5522c764a1e1f75c15a69ebc782f64e
+oid sha256:48d883802cd26d3d087369ab0a65272fa58fbff29eb05b3d7d273c7a73c9014b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8dd217501975c05314f7eae9f4e577905bfff3f368466dd5cff2b1a4f89dfb
+oid sha256:bec563ff0147865a4e688034577bb3a902553d72f9c0ad96bc63b34139260118
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ffac5e1199c240ef0a77f0e1c7f786b8174990a9aefbfe17392a11d4303e0a4
+oid sha256:670c8298a5f8c6db455e44cb4ef11edebb128de2fba584e2f912fee354356a4e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.022559995488000903,
+  "epoch": 0.045119990976001806,
   "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": 16.787,
       "eval_steps_per_second": 4.365,
       "step": 25
+    },
+    {
+      "epoch": 0.02346239530752094,
+      "grad_norm": NaN,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.024364795127040973,
+      "grad_norm": NaN,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.02526719494656101,
+      "grad_norm": NaN,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.026169594766081047,
+      "grad_norm": NaN,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.027071994585601084,
+      "grad_norm": NaN,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.02797439440512112,
+      "grad_norm": NaN,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.028876794224641154,
+      "grad_norm": NaN,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.02977919404416119,
+      "grad_norm": NaN,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.030681593863681227,
+      "grad_norm": NaN,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.031583993683201264,
+      "grad_norm": NaN,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0324863935027213,
+      "grad_norm": NaN,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.03338879332224134,
+      "grad_norm": NaN,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.03429119314176137,
+      "grad_norm": NaN,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.035193592961281404,
+      "grad_norm": NaN,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.036095992780801445,
+      "grad_norm": NaN,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.03699839260032148,
+      "grad_norm": NaN,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.03790079241984152,
+      "grad_norm": NaN,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.03880319223936155,
+      "grad_norm": NaN,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.039705592058881585,
+      "grad_norm": NaN,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.040607991878401625,
+      "grad_norm": NaN,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04151039169792166,
+      "grad_norm": NaN,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0424127915174417,
+      "grad_norm": NaN,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.04331519133696173,
+      "grad_norm": NaN,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.044217591156481766,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.045119990976001806,
+      "grad_norm": NaN,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.045119990976001806,
+      "eval_loss": NaN,
+      "eval_runtime": 2.9828,
+      "eval_samples_per_second": 16.763,
+      "eval_steps_per_second": 4.358,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null