Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ecb59cd3dcc8e9b08abd098f0ce4842cf2cad3509e1f3c3c5ec645880279806
+oid sha256:305172a4233209b332785586535bf2c3d8aca8bc72d082903a8db84c77f208e6
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bceef687e00eb26ad6a325b5da3c7da1c4940b45e035cadfa9cae20209244e0
+oid sha256:78214a0d1c775972f9a80c311a64590edceadfb735370dcdcd5755a2b473c2cb
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d3b7a4a0b65f1ef2a79121dcc36f0f46eec4e9c1f11e716bee10a5e99ef92f
+oid sha256:4ecdfeb4ea872cf0b22fba2a4a5b49827313d1db0a60ec289a0450ef8689f90b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d621dd152a81ceefcc6d5bc8b659af40b059d8f66901d5617810de558ea00786
+oid sha256:72c9642b537a002260f157de61a35183ce8c31d54ef4a119842de582faf6851b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72dbdd06a160ef49790154c5ffb1bdabd6bc430d3425ac68abaddefc26f687a
+oid sha256:c9623f940cc98fa5ce48c7c451ba6138228d9924f883248f3ad6342bbfa49453
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab0db3accd686bcb39bcef79ea6b326c5ddeba4f6221bc32e79fe54bd5ade06
+oid sha256:e71c64ff5dc134b563f75857c691dc2d3e69683266ad3b7566169a083142d621
 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": 0.7876332402229309,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7326007326007326,
+  "best_metric": 0.7660866975784302,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4652014652014653,
   "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": 19.179,
       "eval_steps_per_second": 2.418,
       "step": 25
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.5740500092506409,
+      "learning_rate": 5e-05,
+      "loss": 0.7998,
+      "step": 26
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 1.062048316001892,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7508,
+      "step": 27
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 0.8686541318893433,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7552,
+      "step": 28
+    },
+    {
+      "epoch": 0.8498168498168498,
+      "grad_norm": 0.5461609363555908,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7701,
+      "step": 29
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 0.20379406213760376,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7829,
+      "step": 30
+    },
+    {
+      "epoch": 0.9084249084249084,
+      "grad_norm": 0.48669975996017456,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8228,
+      "step": 31
+    },
+    {
+      "epoch": 0.9377289377289377,
+      "grad_norm": 0.4675156772136688,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.807,
+      "step": 32
+    },
+    {
+      "epoch": 0.967032967032967,
+      "grad_norm": 1.1531270742416382,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.885,
+      "step": 33
+    },
+    {
+      "epoch": 0.9963369963369964,
+      "grad_norm": 0.7078146934509277,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8386,
+      "step": 34
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 1.082878828048706,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.441,
+      "step": 35
+    },
+    {
+      "epoch": 1.054945054945055,
+      "grad_norm": 0.5584947466850281,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7131,
+      "step": 36
+    },
+    {
+      "epoch": 1.0842490842490842,
+      "grad_norm": 0.623293399810791,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7405,
+      "step": 37
+    },
+    {
+      "epoch": 1.1135531135531136,
+      "grad_norm": 0.5018717646598816,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7195,
+      "step": 38
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.893699586391449,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8149,
+      "step": 39
+    },
+    {
+      "epoch": 1.1721611721611722,
+      "grad_norm": 0.6624011397361755,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.81,
+      "step": 40
+    },
+    {
+      "epoch": 1.2014652014652014,
+      "grad_norm": 0.39665865898132324,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7523,
+      "step": 41
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.5487731695175171,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8137,
+      "step": 42
+    },
+    {
+      "epoch": 1.26007326007326,
+      "grad_norm": 0.5722079873085022,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7874,
+      "step": 43
+    },
+    {
+      "epoch": 1.2893772893772895,
+      "grad_norm": 0.6342135071754456,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7224,
+      "step": 44
+    },
+    {
+      "epoch": 1.3186813186813187,
+      "grad_norm": 0.5970407128334045,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7422,
+      "step": 45
+    },
+    {
+      "epoch": 1.347985347985348,
+      "grad_norm": 0.600911557674408,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7389,
+      "step": 46
+    },
+    {
+      "epoch": 1.3772893772893773,
+      "grad_norm": 0.5775716304779053,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7585,
+      "step": 47
+    },
+    {
+      "epoch": 1.4065934065934065,
+      "grad_norm": 0.5375389456748962,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7847,
+      "step": 48
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 0.4871210753917694,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.798,
+      "step": 49
+    },
+    {
+      "epoch": 1.4652014652014653,
+      "grad_norm": 0.7523501515388489,
+      "learning_rate": 0.0,
+      "loss": 0.7955,
+      "step": 50
+    },
+    {
+      "epoch": 1.4652014652014653,
+      "eval_loss": 0.7660866975784302,
+      "eval_runtime": 11.9906,
+      "eval_samples_per_second": 19.182,
+      "eval_steps_per_second": 2.419,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null