Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c932ed5727f1ac5161576c4074c32ca2553c701358607c8d691921b7358aca6
+oid sha256:e1cb96d73ffd9b18bfed97c7cf10bd7669d22633573eaba2c8758a8d13f2a975
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfa2dac4702fdf0e9ba6e21ac0b5243fb890324ddcc44293cec80e0e5be3cc1
+oid sha256:9d14342bd01e68363625e0387d2d059757e95aa739e756ec6711e10f76bbe707
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de38d0cc31cd3a0be25ab9a03e58b66501bb37e3efe88c548a90dfdc604c66ba
+oid sha256:cda7e6c97ef8e098683e8cea7066498818983bc139a453e3f042ee4cf4ecbd52
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de74a85d1d375f5dd9e7bbc9505b0ab39bce63d28a357dc0a5ef4c50e537a364
+oid sha256:6babfa4189f767a6f507beefeae142d9b9a2df2ba0a481acba3ee30ddec5ed13
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d435b5fd9aedfd8e7d6cdf54b1ac4c486d501414fa5307ad21a00ca82434917a
+oid sha256:fb582efafc8c8283e7e7dc6313e40f317b6c79a6816fb47f99598470babb6534
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5cbaca775b0fe3dfd371dc5fd41aad7e4dd0b59fec1975a91bcbf8a87c7c80f
+oid sha256:3e5ab6a5462065c804a587a02aefedefcd4d73cf5245c0bad6584c01b2a3bdc1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4527629233511585,
+  "epoch": 2.905525846702317,
   "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": 11.583,
       "eval_steps_per_second": 3.012,
       "step": 25
+    },
+    {
+      "epoch": 1.5098039215686274,
+      "grad_norm": NaN,
+      "learning_rate": 5.9152076175848594e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.5668449197860963,
+      "grad_norm": NaN,
+      "learning_rate": 5.6385777635027684e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.6238859180035652,
+      "grad_norm": NaN,
+      "learning_rate": 5.361422236497235e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.6809269162210339,
+      "grad_norm": NaN,
+      "learning_rate": 5.0847923824151424e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.7379679144385025,
+      "grad_norm": NaN,
+      "learning_rate": 4.809737553045916e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.7950089126559714,
+      "grad_norm": NaN,
+      "learning_rate": 4.537301125570763e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.8520499108734403,
+      "grad_norm": NaN,
+      "learning_rate": 4.268516544675628e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": NaN,
+      "learning_rate": 4.004403402341532e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.966131907308378,
+      "grad_norm": NaN,
+      "learning_rate": 3.7459635701829435e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.049910873440285,
+      "grad_norm": NaN,
+      "learning_rate": 3.494177399005578e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.106951871657754,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.163992869875223,
+      "grad_norm": NaN,
+      "learning_rate": 3.014357621677724e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.2210338680926918,
+      "grad_norm": NaN,
+      "learning_rate": 2.7881441362933468e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.2780748663101607,
+      "grad_norm": NaN,
+      "learning_rate": 2.5722176490809118e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.335115864527629,
+      "grad_norm": NaN,
+      "learning_rate": 2.3673972431668306e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.392156862745098,
+      "grad_norm": NaN,
+      "learning_rate": 2.1744598725070347e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.449197860962567,
+      "grad_norm": NaN,
+      "learning_rate": 1.994137414634483e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.5062388591800357,
+      "grad_norm": NaN,
+      "learning_rate": 1.827113894397003e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.5632798573975046,
+      "grad_norm": NaN,
+      "learning_rate": 1.674022889216737e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.620320855614973,
+      "grad_norm": NaN,
+      "learning_rate": 1.53544512571397e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.677361853832442,
+      "grad_norm": NaN,
+      "learning_rate": 1.4119062768121433e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.734402852049911,
+      "grad_norm": NaN,
+      "learning_rate": 1.3038749676803994e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.7914438502673797,
+      "grad_norm": NaN,
+      "learning_rate": 1.2117609980777959e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": NaN,
+      "learning_rate": 1.1359137878424578e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.905525846702317,
+      "grad_norm": NaN,
+      "learning_rate": 1.076621051422442e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.905525846702317,
+      "eval_loss": NaN,
+      "eval_runtime": 4.3476,
+      "eval_samples_per_second": 11.501,
+      "eval_steps_per_second": 2.99,
+      "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": 2.8346698791124992e+17,
+  "total_flos": 5.6711086619806925e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null