Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52fa27302531f4437769fcda624601d8edc9311da3d450aeabd16d1ff947b017
+oid sha256:b27d0caec6afc24e5b59d2ebedae663163cb6b271887efd13d4389bb7019db18
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b45f989a3b3579dfbaa22cd0d16196498d84ad49993eb67fb2f7ed836283ad3f
+oid sha256:a05726c02fbf8476b07a8d323724abcfee65084dcf82abf7eb829058b9aa9085
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c511cf90a13a360de4206b63de486ccccdfee8e39609f78397498b3142acbe7
+oid sha256:f2f05c372b3fa51f0656efea74a9ab2b107c6f227e5c30bb197298253f736e5f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5af96c1e53d1efd9cf84bb92d8841a4af382a47c44eef8800c7f0b37c2d4bfd
+oid sha256:cd0d1e65afcdb520fa182410b178b6cd296da96c4c57616ed421c0bf2cd34e45
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a4cc4e04f6fb1b242e701dca46be65a5a2858bcca07b1fe7b9ab2d403b7061
+oid sha256:3508229b6a54dbfb9f1bb0bff7e4acc87c9b7421621b34bca4e0836705a4d70d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9e7a6520e3374c49a2b87e33f2534f7d79378989c363c8df3e7c5d3dc23188
+oid sha256:093562d359fd9c5066e7dc86cf4df453730a9d676f29b5bf8bcc7c9e735082dc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.915375709533691,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.032002560204816385,
+  "best_metric": 10.859091758728027,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06400512040963277,
   "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": 895.049,
       "eval_steps_per_second": 111.902,
       "step": 25
+    },
+    {
+      "epoch": 0.033282662613009044,
+      "grad_norm": 9.160806655883789,
+      "learning_rate": 5e-05,
+      "loss": 10.9391,
+      "step": 26
+    },
+    {
+      "epoch": 0.034562765021201695,
+      "grad_norm": 8.870255470275879,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.9376,
+      "step": 27
+    },
+    {
+      "epoch": 0.035842867429394354,
+      "grad_norm": 9.3232421875,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.9196,
+      "step": 28
+    },
+    {
+      "epoch": 0.037122969837587005,
+      "grad_norm": 9.68075942993164,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.8989,
+      "step": 29
+    },
+    {
+      "epoch": 0.038403072245779664,
+      "grad_norm": 9.822731018066406,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.8904,
+      "step": 30
+    },
+    {
+      "epoch": 0.039683174653972315,
+      "grad_norm": 10.109760284423828,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.8711,
+      "step": 31
+    },
+    {
+      "epoch": 0.040963277062164974,
+      "grad_norm": 10.420609474182129,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.8687,
+      "step": 32
+    },
+    {
+      "epoch": 0.042243379470357625,
+      "grad_norm": 10.236992835998535,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.8692,
+      "step": 33
+    },
+    {
+      "epoch": 0.043523481878550284,
+      "grad_norm": 10.572797775268555,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.8552,
+      "step": 34
+    },
+    {
+      "epoch": 0.04480358428674294,
+      "grad_norm": 10.187577247619629,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.8572,
+      "step": 35
+    },
+    {
+      "epoch": 0.046083686694935594,
+      "grad_norm": 10.250493049621582,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.8482,
+      "step": 36
+    },
+    {
+      "epoch": 0.04736378910312825,
+      "grad_norm": 9.556073188781738,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.8744,
+      "step": 37
+    },
+    {
+      "epoch": 0.048643891511320904,
+      "grad_norm": 9.524937629699707,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.8739,
+      "step": 38
+    },
+    {
+      "epoch": 0.04992399391951356,
+      "grad_norm": 8.893146514892578,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.8919,
+      "step": 39
+    },
+    {
+      "epoch": 0.051204096327706214,
+      "grad_norm": 9.009846687316895,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.8814,
+      "step": 40
+    },
+    {
+      "epoch": 0.05248419873589887,
+      "grad_norm": 8.93393611907959,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.8815,
+      "step": 41
+    },
+    {
+      "epoch": 0.053764301144091524,
+      "grad_norm": 9.061225891113281,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.8766,
+      "step": 42
+    },
+    {
+      "epoch": 0.05504440355228418,
+      "grad_norm": 9.76646614074707,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.8549,
+      "step": 43
+    },
+    {
+      "epoch": 0.05632450596047684,
+      "grad_norm": 10.304689407348633,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.8355,
+      "step": 44
+    },
+    {
+      "epoch": 0.05760460836866949,
+      "grad_norm": 9.984641075134277,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.8481,
+      "step": 45
+    },
+    {
+      "epoch": 0.05888471077686215,
+      "grad_norm": 9.914651870727539,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.8374,
+      "step": 46
+    },
+    {
+      "epoch": 0.0601648131850548,
+      "grad_norm": 9.991412162780762,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.8372,
+      "step": 47
+    },
+    {
+      "epoch": 0.06144491559324746,
+      "grad_norm": 10.301223754882812,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.837,
+      "step": 48
+    },
+    {
+      "epoch": 0.06272501800144012,
+      "grad_norm": 9.447504043579102,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.8695,
+      "step": 49
+    },
+    {
+      "epoch": 0.06400512040963277,
+      "grad_norm": 10.3909273147583,
+      "learning_rate": 0.0,
+      "loss": 10.8582,
+      "step": 50
+    },
+    {
+      "epoch": 0.06400512040963277,
+      "eval_loss": 10.859091758728027,
+      "eval_runtime": 5.8597,
+      "eval_samples_per_second": 898.169,
+      "eval_steps_per_second": 112.292,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 19055561932800.0,
+  "total_flos": 38111123865600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null