Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b211233ce22145c3f87417e84548849ea7e1b8606ecaad7344db988c36b21fa2
+oid sha256:b91bcb68eebf0dc2dc7095eab1b2acc42bd75fbe5140ce24210e729d64bc2254
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd0544bebffa1a54065b23d7971a5ca10d9a271e78577c93e6d4c08e7d8ce9f
+oid sha256:59c89a4494d6622f7b42203b3829e1cab92562131a38f042df385d133c130544
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca7bbeab95ad026615a6f28dea696e055710644591e9160f0ae043ad302b9d0
+oid sha256:79cbd84430ea1359217645e8ec1f000eac283825bdc203b0ac13e770ea617acf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90def4a99473236b88382b0760ac4e7b19ec397c8f2ed8f1a3213a98ad66a53f
+oid sha256:fe4f7f4f86b1e2e1a0bf419afb4bf9e379bd879b3be40ea2c41cf9ff0ca602ad
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c3366759bf458e33e5e9704eac0ed0d3f4b33973620658e14bd3fba8119b56
+oid sha256:b49066405a857894cb0999b4893d02a7bfec71b25cf121871934e5864d4e71e9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c780a8b6699ec3027ee436f5f3202c115dddc8b349b02577f90e8e2f95c029ca
+oid sha256:a91c83173e04da93153aa595f3b4a73e07a36b0b4a8eabfdf5df79b831a2edd0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8547008547008547,
+  "epoch": 1.7094017094017095,
   "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": 44.101,
       "eval_steps_per_second": 11.466,
       "step": 25
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": NaN,
+      "learning_rate": 8.469660406954253e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": NaN,
+      "learning_rate": 8.342699528139629e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": NaN,
+      "learning_rate": 8.211855863706654e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "grad_norm": NaN,
+      "learning_rate": 8.077308130362274e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": NaN,
+      "learning_rate": 7.939240104126023e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.0598290598290598,
+      "grad_norm": NaN,
+      "learning_rate": 7.797840369314081e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.0940170940170941,
+      "grad_norm": NaN,
+      "learning_rate": 7.653302060955789e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.1282051282051282,
+      "grad_norm": NaN,
+      "learning_rate": 7.505822600994424e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.1623931623931625,
+      "grad_norm": NaN,
+      "learning_rate": 7.355603428632566e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": NaN,
+      "learning_rate": 7.202849725190397e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": NaN,
+      "learning_rate": 7.047770133852677e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 1.264957264957265,
+      "grad_norm": NaN,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 1.2991452991452992,
+      "grad_norm": NaN,
+      "learning_rate": 6.731483455324374e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 6.570708377691784e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": NaN,
+      "learning_rate": 6.408470841206546e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.4017094017094016,
+      "grad_norm": NaN,
+      "learning_rate": 6.244992442828586e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": NaN,
+      "learning_rate": 6.0804964743859164e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 1.4700854700854702,
+      "grad_norm": NaN,
+      "learning_rate": 5.9152076175848594e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 1.5042735042735043,
+      "grad_norm": NaN,
+      "learning_rate": 5.749351637121866e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": NaN,
+      "learning_rate": 5.5831550723160856e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 1.5726495726495726,
+      "grad_norm": NaN,
+      "learning_rate": 5.416844927683916e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 1.606837606837607,
+      "grad_norm": NaN,
+      "learning_rate": 5.250648362878135e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": NaN,
+      "learning_rate": 5.0847923824151424e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 1.6752136752136753,
+      "grad_norm": NaN,
+      "learning_rate": 4.919503525614087e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": NaN,
+      "learning_rate": 4.7550075571714146e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "eval_loss": NaN,
+      "eval_runtime": 1.1173,
+      "eval_samples_per_second": 44.749,
+      "eval_steps_per_second": 11.635,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null