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:f1d548362eccfc41b223d549c0498888b427271cc05fcd5ebe06a8b6323c1d84
+oid sha256:20e48d272edec54e760cc921a22121ecfdac6a2100cf9bde7580dbca4f54e372
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eebc994f12c64c80834b9759f432bf2fefb261af1808962df417651a6242a03
+oid sha256:85133fc719ea4db801669d36609aee8880ecd7c66b8a7ce24ec9560a12c972b2
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb679fe3d490daef838a90064adb8f5538e2c54cbd029486dbadcd4e889b823e
+oid sha256:7b5ff8068b6e40a54aac45b5ab165e7c045738bd76af153a089fd3cc2a4ce668
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d51428e2743aa14705b645249536dfcb699f4dbc21f8b1d8e83322bf099bb5
+oid sha256:9a65a04caf196d147a07f9a9854b0432df58785ad910ab2a1524d1d6bba25fba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7f7ce2fa15b355f0331aa63627bed5a8e8bbcb0b45671a6c28e142fa7f6512
+oid sha256:09c3df3f4f771c21cb9741437fc7d9b869cfc8ce8c7ce9ceb10a9d7e4f44a020
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45aa370544264fedf0602909f4d91b4cd4918794218a44f2c2144f29899e9000
+oid sha256:b15742aa97b67892928dd76c23f0482d2d8a41f5793554a76f2b79b43af000fa
 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": 0.217138409614563,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2828854314002829,
+  "best_metric": 0.10270044952630997,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5657708628005658,
   "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": 39.568,
       "eval_steps_per_second": 4.988,
       "step": 25
+    },
+    {
+      "epoch": 0.2942008486562942,
+      "grad_norm": 0.08450052887201309,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 26
+    },
+    {
+      "epoch": 0.3055162659123055,
+      "grad_norm": 5.7550835609436035,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0396,
+      "step": 27
+    },
+    {
+      "epoch": 0.31683168316831684,
+      "grad_norm": 3.7565834522247314,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0744,
+      "step": 28
+    },
+    {
+      "epoch": 0.32814710042432815,
+      "grad_norm": 1.2026886940002441,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0131,
+      "step": 29
+    },
+    {
+      "epoch": 0.33946251768033947,
+      "grad_norm": 0.4069508910179138,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0088,
+      "step": 30
+    },
+    {
+      "epoch": 0.3507779349363508,
+      "grad_norm": 0.40454617142677307,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0063,
+      "step": 31
+    },
+    {
+      "epoch": 0.3620933521923621,
+      "grad_norm": 4.627459526062012,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0733,
+      "step": 32
+    },
+    {
+      "epoch": 0.3734087694483734,
+      "grad_norm": 2.0707437992095947,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0246,
+      "step": 33
+    },
+    {
+      "epoch": 0.38472418670438474,
+      "grad_norm": 2.672361373901367,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2179,
+      "step": 34
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 5.646185874938965,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4478,
+      "step": 35
+    },
+    {
+      "epoch": 0.4073550212164074,
+      "grad_norm": 3.170839309692383,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3974,
+      "step": 36
+    },
+    {
+      "epoch": 0.4186704384724187,
+      "grad_norm": 3.557582139968872,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4034,
+      "step": 37
+    },
+    {
+      "epoch": 0.42998585572843,
+      "grad_norm": 0.8311156034469604,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1684,
+      "step": 38
+    },
+    {
+      "epoch": 0.44130127298444133,
+      "grad_norm": 0.007551469840109348,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0001,
+      "step": 39
+    },
+    {
+      "epoch": 0.4526166902404526,
+      "grad_norm": 0.09443239122629166,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0011,
+      "step": 40
+    },
+    {
+      "epoch": 0.4639321074964639,
+      "grad_norm": 0.03768008202314377,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0005,
+      "step": 41
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 0.31332749128341675,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0033,
+      "step": 42
+    },
+    {
+      "epoch": 0.48656294200848654,
+      "grad_norm": 1.8230053186416626,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0182,
+      "step": 43
+    },
+    {
+      "epoch": 0.49787835926449786,
+      "grad_norm": 2.7197210788726807,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0416,
+      "step": 44
+    },
+    {
+      "epoch": 0.5091937765205092,
+      "grad_norm": 0.6926154494285583,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0082,
+      "step": 45
+    },
+    {
+      "epoch": 0.5205091937765205,
+      "grad_norm": 1.0953466892242432,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1237,
+      "step": 46
+    },
+    {
+      "epoch": 0.5318246110325319,
+      "grad_norm": 2.7397115230560303,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.325,
+      "step": 47
+    },
+    {
+      "epoch": 0.5431400282885431,
+      "grad_norm": 1.0948930978775024,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.345,
+      "step": 48
+    },
+    {
+      "epoch": 0.5544554455445545,
+      "grad_norm": 1.4320255517959595,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3015,
+      "step": 49
+    },
+    {
+      "epoch": 0.5657708628005658,
+      "grad_norm": 0.5962116122245789,
+      "learning_rate": 0.0,
+      "loss": 0.2995,
+      "step": 50
+    },
+    {
+      "epoch": 0.5657708628005658,
+      "eval_loss": 0.10270044952630997,
+      "eval_runtime": 15.0801,
+      "eval_samples_per_second": 39.456,
+      "eval_steps_per_second": 4.973,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null