Training in progress, step 37, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa94c6ebd9b1b2145bbc8bdba9f52958fda6db63ad2ab54451bb1feb9dd40d74
+oid sha256:ebcdc06844f452ee7c310f654f69e21ae664d5ebb01d68559119fb5e2cb9a19e
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1053cd5c03cb59750bf53f7deb2bc14bae898a9fccb7e2e82b167442c8a3d08d
+oid sha256:4ead7123f358612ad8d5ee2c8f95e6746ef1c3641f2016f18fc4ea0840ec06c2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a796d7776608c6bc1a01bc95265d87a7456a6c92bfa70dcfee7f8c0ece9c61
+oid sha256:529542a07015b0068b0b8d89ceb0607eb91d14b6e7661d051a99ed148e6f4ecc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04a9222f4ef263bbbd8baf094dd94a5c7db82676535bdc51514e9fe6976723b
+oid sha256:cc8e6c822f71c16b21e7907ea537ab89eb1f1137c0448b9cc4af846ad3006438
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f8d82572679f82e619172f2520821ceb9d69328900426666e1fe3fae47b09e
+oid sha256:b17dbd4cb3397eabdfa00a63d0b64aa050069f059f3646d93a1271a1273d6d1a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:178f9dbd9d72f6e0ee917396246b63cd211b095b3f0fe3078785d250d96bac6c
+oid sha256:e1df0c22090f509867cb1f8fd81877850d90a52f2fa21e66515d4ed39ac5f588
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.0618556701030926,
+  "epoch": 3.051546391752577,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 37,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,90 @@
       "eval_samples_per_second": 7.992,
       "eval_steps_per_second": 2.078,
       "step": 25
+    },
+    {
+      "epoch": 2.1443298969072164,
+      "grad_norm": NaN,
+      "learning_rate": 3.0209635834655392e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.2268041237113403,
+      "grad_norm": NaN,
+      "learning_rate": 2.6942958916356998e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.3092783505154637,
+      "grad_norm": NaN,
+      "learning_rate": 2.3902180795591093e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.3917525773195876,
+      "grad_norm": NaN,
+      "learning_rate": 2.111178402983751e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.4742268041237114,
+      "grad_norm": NaN,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.556701030927835,
+      "grad_norm": NaN,
+      "learning_rate": 1.6369804287916028e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.6391752577319587,
+      "grad_norm": NaN,
+      "learning_rate": 1.4456400944391146e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.7216494845360826,
+      "grad_norm": NaN,
+      "learning_rate": 1.2869430821211828e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.804123711340206,
+      "grad_norm": NaN,
+      "learning_rate": 1.1621671268686606e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.88659793814433,
+      "grad_norm": NaN,
+      "learning_rate": 1.0723168513061666e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.9690721649484537,
+      "grad_norm": NaN,
+      "learning_rate": 1.0181156770214243e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 3.051546391752577,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 37
     }
   ],
   "logging_steps": 1,
@@ -221,12 +305,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.926288903186678e+17,
+  "total_flos": 5.784250223102525e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null