Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bbe0f56dcbb5789c4b5a3765af8c8eb4aefdab5fa77b4b8b7e2ea4e497c8658
+oid sha256:4a0829c05678a90eab71189be6f29b9448e3ef930f0c85e061a8f9bee98674c5
 size 78504446

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48765d3dd339137a28e1879b1a7d9acdff5293f4bdc05e065283591320f6c15c
+oid sha256:aa255261495bb42417f3a162674b78dfc813207afc5cc668d356529c0bf8ec64
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d317bf94fa0153cdb8133d3e817543e744c37aff4b829fc160dc2e9f5ea0fb
+oid sha256:ae00d53a5d2d3909f538281639eeb056103554bd614eb366596520ebe05f096c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a5490064378ab8d1d09a0e06f911a1df3499424be9f5c030a3985e80481766
+oid sha256:5033c23b1256545e3958781c91d05aa049e125742f78146cebfaa7b8e5dee8d3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef4a93b2ff250931b8fca76425267056ae9a1b407526601cb6d81e4e9e498d86
+oid sha256:426ae5ccaae99d927de0d80c4bae0c740856d09e05c9b8159a85da62dbc9c1aa
 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": 0.21522733387140167,
+  "epoch": 0.43045466774280333,
   "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": 90.9,
       "eval_steps_per_second": 23.634,
       "step": 25
+    },
+    {
+      "epoch": 0.22383642722625774,
+      "grad_norm": NaN,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.2324455205811138,
+      "grad_norm": NaN,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.24105461393596986,
+      "grad_norm": NaN,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.24966370729082593,
+      "grad_norm": NaN,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.258272800645682,
+      "grad_norm": NaN,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2668818940005381,
+      "grad_norm": NaN,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.2754909873553941,
+      "grad_norm": NaN,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.2841000807102502,
+      "grad_norm": NaN,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.29270917406510627,
+      "grad_norm": NaN,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.3013182674199623,
+      "grad_norm": NaN,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.3099273607748184,
+      "grad_norm": NaN,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.31853645412967446,
+      "grad_norm": NaN,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.3271455474845305,
+      "grad_norm": NaN,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.3357546408393866,
+      "grad_norm": NaN,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.34436373419424265,
+      "grad_norm": NaN,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.35297282754909876,
+      "grad_norm": NaN,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.3615819209039548,
+      "grad_norm": NaN,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.37019101425881085,
+      "grad_norm": NaN,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.37880010761366695,
+      "grad_norm": NaN,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": NaN,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.3960182943233791,
+      "grad_norm": NaN,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.40462738767823514,
+      "grad_norm": NaN,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.4132364810330912,
+      "grad_norm": NaN,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.4218455743879473,
+      "grad_norm": NaN,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.43045466774280333,
+      "grad_norm": NaN,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.43045466774280333,
+      "eval_loss": NaN,
+      "eval_runtime": 0.5432,
+      "eval_samples_per_second": 92.045,
+      "eval_steps_per_second": 23.932,
+      "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": 4567346303729664.0,
+  "total_flos": 9137542754467840.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null