Training in progress, step 46, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451f31ccfddec7f804b7b048741a816ff9e1e5e9e21f222208897467b23fb640
+oid sha256:c24da4351a9cea749143ae9343eb7f846f579a21b68c3ef96282de323f7e8c40
 size 9067978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f32352e199d24d42c0ff07b6c2353730ffff136c8a073617125a6598012db5b9
+oid sha256:bedc5947b73c5ba764275c0a6c42f40afdba230165e89bc88642fd0b4cc9770d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f02d9382565458d320cfed4ba0f47f8a29cb92c0872adc4ff9f09f6b64f341a
+oid sha256:c25cb327038df47d366d54b7d2c05b3a779fb45a19eb987f7ad391e9c133fd91
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01d73031aea22597b9ff1097828337e92846d58e42e130a1bf2e44be9f6f191
+oid sha256:6a48d1598274d41544b4997c92a4a64afd5332997540f10d239ebc8b1e1063d2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46880894db029c743cc1bd9d00d6eca355f19506ab4485a81d0922f3e3f5db2b
+oid sha256:8edca5b1fa1bdca5516df74677be03a0d604a547a6ef27a7e9bfca275c8b736b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c559cbde9153c17d7a372e6ef412013941e6297ae86a5518b43caf90efbb1f
+oid sha256:b7f1ee7e5310274a73405630534a716def8b331763fa23521c74926adf94696e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6528925619834711,
+  "epoch": 3.041322314049587,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 46,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,153 @@
       "eval_samples_per_second": 552.928,
       "eval_steps_per_second": 70.471,
       "step": 25
+    },
+    {
+      "epoch": 1.71900826446281,
+      "grad_norm": NaN,
+      "learning_rate": 4.288425808633575e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.7851239669421488,
+      "grad_norm": NaN,
+      "learning_rate": 3.937173552235117e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.8512396694214877,
+      "grad_norm": NaN,
+      "learning_rate": 3.591337215792852e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.9173553719008265,
+      "grad_norm": NaN,
+      "learning_rate": 3.2526791020045086e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.9834710743801653,
+      "grad_norm": NaN,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.049586776859504,
+      "grad_norm": NaN,
+      "learning_rate": 2.603755066399718e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.115702479338843,
+      "grad_norm": NaN,
+      "learning_rate": 2.296795912722014e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": NaN,
+      "learning_rate": 2.0036116674432654e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.2479338842975207,
+      "grad_norm": NaN,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.3140495867768593,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.3801652892561984,
+      "grad_norm": NaN,
+      "learning_rate": 1.2212521282287092e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.446280991735537,
+      "grad_norm": NaN,
+      "learning_rate": 9.972937953781986e-06,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.512396694214876,
+      "grad_norm": NaN,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.5785123966942147,
+      "grad_norm": NaN,
+      "learning_rate": 6.116050521637218e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.644628099173554,
+      "grad_norm": NaN,
+      "learning_rate": 4.5184002322740785e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.7107438016528924,
+      "grad_norm": NaN,
+      "learning_rate": 3.1525137500119207e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.7768595041322315,
+      "grad_norm": NaN,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.84297520661157,
+      "grad_norm": NaN,
+      "learning_rate": 1.1426567014420297e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": NaN,
+      "learning_rate": 5.089279059533658e-07,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.975206611570248,
+      "grad_norm": NaN,
+      "learning_rate": 1.2739426948732424e-07,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 3.041322314049587,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 46
     }
   ],
   "logging_steps": 1,
@@ -221,12 +368,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1753141896806400.0,
+  "total_flos": 3225781090123776.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null