Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cecc2881172a06212c498084aed8741ebc8feabe92879564d873f9b5da8afc7
+oid sha256:1a009ea5c91447268fca208d329fa0c8e69cb7b18d0fcb4c3edc3262d0c59917
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2b2f8615a848d5c4bb48adab9bb3e49391f9f7c6622b72b0b55e21a1ccb584
+oid sha256:5234d7a44c0ae18c54219fc7e73bd5a13dc0c4bd1baf9dec44cf7911ecea7229
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a66ca9d46d849c2d102e98d3729a55261719de27e54633a6205f8096f28276
+oid sha256:95148e18ccbdf905670246ec0688e9256a50548d2f50bb626bd9c7590a201299
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c19d6eec0f8267738347b60ed3ebb3bf4c6064b41d5cf38c0eacfd41c2b29f
+oid sha256:aaa8f3a08e1130750ef79c0c647d4b187a809e8d6efbff8a9c81195ae4249fc0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7580a1dd31343cd568e3e9f3f1a08360ee1ca0466a148375cf916cf1ba7b66
+oid sha256:bb65a576d95170738cdf27db95ece9a1b104bf7795b2774c20e960daea3298eb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b53322a9e0770f1aa889f3dc8eda417cbde627f634c75503b1e43849ff496ab
+oid sha256:d50872ebe2ae52bfb0e335aaa2e28a3dac724479a77b01ce7ef36e8156017c85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.048780487804878,
+  "epoch": 3.1902439024390246,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,104 @@
       "eval_samples_per_second": 9.458,
       "eval_steps_per_second": 2.459,
       "step": 25
+    },
+    {
+      "epoch": 2.126829268292683,
+      "grad_norm": NaN,
+      "learning_rate": 3.474083148320469e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.204878048780488,
+      "grad_norm": NaN,
+      "learning_rate": 3.1406172239924584e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.2829268292682925,
+      "grad_norm": NaN,
+      "learning_rate": 2.8241507066307104e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.3609756097560974,
+      "grad_norm": NaN,
+      "learning_rate": 2.5269637447446348e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": NaN,
+      "learning_rate": 2.2511975772046403e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.5170731707317073,
+      "grad_norm": NaN,
+      "learning_rate": 1.9988391055670233e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.5951219512195123,
+      "grad_norm": NaN,
+      "learning_rate": 1.771706578402711e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.6731707317073172,
+      "grad_norm": NaN,
+      "learning_rate": 1.5714364907746536e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.7512195121951217,
+      "grad_norm": NaN,
+      "learning_rate": 1.3994717932533891e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.8292682926829267,
+      "grad_norm": NaN,
+      "learning_rate": 1.257051495425121e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.9073170731707316,
+      "grad_norm": NaN,
+      "learning_rate": 1.1452017387992552e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 3.0341463414634147,
+      "grad_norm": NaN,
+      "learning_rate": 1.064728403435312e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 3.1121951219512196,
+      "grad_norm": NaN,
+      "learning_rate": 1.0162113015586309e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 3.1902439024390246,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -221,12 +319,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.460553118591222e+17,
+  "total_flos": 5.33933996183126e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null