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:b3c927940510721a0aa8f2c265e7752f55c7b1be6e6c5f722295c2841c9da998
+oid sha256:e62472539b057953ba2836d9367bba2581f77776d105ef62ecb51fde9d986600
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07ca49d7ac5f6baec86a930e0f6f5c187bc574e95fd739d8203ac0e7fe5cd07
+oid sha256:2cbd2d85a200b3fed63d14d96b5fb112deb72bdb9753ed89fef32b81783282d2
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a323daa8860fff4c126c820e7286237fb4c7f0315374fa19f737402969ad34
+oid sha256:71df2eba219d9b7422d895902584d1315438f2d9ea557ec440b083e9857c72ad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a831882486e14a123a53f1c3fb585642be2514564bc34d8d691f4279d08785
+oid sha256:93c21195a4dccd0927844088cb1cfa8ca6f7e62b94dd3b0a4ab82838fdd2bf12
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e8463c92561aa9d2dd1c235a83939bdf62a73a8d02f79a7df15b32d8b6dc5e
+oid sha256:d7cc19b826572a56f4db0be727aa4a5f6930e625c39d8a5bb01281844f1c862f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea01c768893f2b99171f0519f44c483a9827173112040f3f0b687ed03056fa22
+oid sha256:99a32005d178f46a67a1ac2dfb89052fcf710d72019b6e846ca97e3cb2dc9238
 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": 0.543145477771759,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.13311148086522462,
+  "best_metric": 0.2183598130941391,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.26622296173044924,
   "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": 33.72,
       "eval_steps_per_second": 4.238,
       "step": 25
+    },
+    {
+      "epoch": 0.13843594009983362,
+      "grad_norm": 4.257485866546631,
+      "learning_rate": 5e-05,
+      "loss": 0.5404,
+      "step": 26
+    },
+    {
+      "epoch": 0.1437603993344426,
+      "grad_norm": 4.45656156539917,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.57,
+      "step": 27
+    },
+    {
+      "epoch": 0.14908485856905157,
+      "grad_norm": 3.2174301147460938,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4359,
+      "step": 28
+    },
+    {
+      "epoch": 0.15440931780366057,
+      "grad_norm": 1.8433396816253662,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3289,
+      "step": 29
+    },
+    {
+      "epoch": 0.15973377703826955,
+      "grad_norm": 1.776909589767456,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3473,
+      "step": 30
+    },
+    {
+      "epoch": 0.16505823627287852,
+      "grad_norm": 2.0475502014160156,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.338,
+      "step": 31
+    },
+    {
+      "epoch": 0.17038269550748752,
+      "grad_norm": 3.002129316329956,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3206,
+      "step": 32
+    },
+    {
+      "epoch": 0.1757071547420965,
+      "grad_norm": 2.487653970718384,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2816,
+      "step": 33
+    },
+    {
+      "epoch": 0.1810316139767055,
+      "grad_norm": 2.3512144088745117,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3687,
+      "step": 34
+    },
+    {
+      "epoch": 0.18635607321131448,
+      "grad_norm": 1.3423824310302734,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2889,
+      "step": 35
+    },
+    {
+      "epoch": 0.19168053244592345,
+      "grad_norm": 2.7216291427612305,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3866,
+      "step": 36
+    },
+    {
+      "epoch": 0.19700499168053245,
+      "grad_norm": 1.77122962474823,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3026,
+      "step": 37
+    },
+    {
+      "epoch": 0.20232945091514143,
+      "grad_norm": 2.95351505279541,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3089,
+      "step": 38
+    },
+    {
+      "epoch": 0.2076539101497504,
+      "grad_norm": 1.4593188762664795,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2316,
+      "step": 39
+    },
+    {
+      "epoch": 0.2129783693843594,
+      "grad_norm": 1.3390860557556152,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1849,
+      "step": 40
+    },
+    {
+      "epoch": 0.21830282861896838,
+      "grad_norm": 1.160514235496521,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1797,
+      "step": 41
+    },
+    {
+      "epoch": 0.22362728785357738,
+      "grad_norm": 1.867867112159729,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2385,
+      "step": 42
+    },
+    {
+      "epoch": 0.22895174708818636,
+      "grad_norm": 1.830309510231018,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1784,
+      "step": 43
+    },
+    {
+      "epoch": 0.23427620632279533,
+      "grad_norm": 1.401082992553711,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1683,
+      "step": 44
+    },
+    {
+      "epoch": 0.23960066555740434,
+      "grad_norm": 1.363930106163025,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1922,
+      "step": 45
+    },
+    {
+      "epoch": 0.2449251247920133,
+      "grad_norm": 1.3577070236206055,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1874,
+      "step": 46
+    },
+    {
+      "epoch": 0.2502495840266223,
+      "grad_norm": 1.2456406354904175,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2281,
+      "step": 47
+    },
+    {
+      "epoch": 0.2555740432612313,
+      "grad_norm": 1.244443655014038,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2101,
+      "step": 48
+    },
+    {
+      "epoch": 0.2608985024958403,
+      "grad_norm": 1.5903034210205078,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2462,
+      "step": 49
+    },
+    {
+      "epoch": 0.26622296173044924,
+      "grad_norm": 3.396489143371582,
+      "learning_rate": 0.0,
+      "loss": 0.5009,
+      "step": 50
+    },
+    {
+      "epoch": 0.26622296173044924,
+      "eval_loss": 0.2183598130941391,
+      "eval_runtime": 37.1668,
+      "eval_samples_per_second": 34.036,
+      "eval_steps_per_second": 4.278,
+      "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": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null