Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f799a677b4a19e1448fa8f70e36fae0e7d08f7f98f55d0419540ae3d78f708
+oid sha256:9355c46d404d8192a3c4b61d815d66e74cdd87bf80de6a35b82cc83d8dc525a5
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7940042f408260332a07a7f46c844852006b8c7f00e1126710bdb319a6b39f8d
+oid sha256:38e5d55c6f9059b076b1cd272ab355ec72046926d892e4a85538d29214fb924f
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e82c08768458f29557d2b6b0461cdcd167b0b9c4f3f8db3f6a0508db17abd4
+oid sha256:70e13c13b14d3afcc8cf66bb1d903848585304d2ee8c3c8c3059646657d3d910
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa78b5157fc8b671a0cb8e338e143e30d7fd7fbb734ea88bfedd91ccaf677f5
+oid sha256:fdea8f42abdfa4eb742d290332aeefea47c29664b6260904e7f44fbe63d62636
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27ebd23309501d436e655ae4c84f0872177366adde31e61a6b06e6e04031abc
+oid sha256:7653f24341f5370dcd959e00770c6d0f40d0d1da5db7840766fa44d753c04716
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ad135cfd4b12a8283774f6059a1a709c9eb78edecfb176579e4a713f60eba9
+oid sha256:75a64a210fbc8969afba286d57c0eed0fce1175d55147ddd0ad8c7ac2ca80918
 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": 0.27160951495170593,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03194633016532226,
+  "best_metric": 0.22318783402442932,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06389266033064452,
   "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": 20.167,
       "eval_steps_per_second": 2.521,
       "step": 25
+    },
+    {
+      "epoch": 0.03322418337193515,
+      "grad_norm": 1.3373982906341553,
+      "learning_rate": 5e-05,
+      "loss": 0.7826,
+      "step": 26
+    },
+    {
+      "epoch": 0.03450203657854804,
+      "grad_norm": 0.9719566702842712,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4262,
+      "step": 27
+    },
+    {
+      "epoch": 0.03577988978516093,
+      "grad_norm": 0.765075147151947,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3854,
+      "step": 28
+    },
+    {
+      "epoch": 0.03705774299177382,
+      "grad_norm": 0.6298338770866394,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2725,
+      "step": 29
+    },
+    {
+      "epoch": 0.03833559619838671,
+      "grad_norm": 0.47626811265945435,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2295,
+      "step": 30
+    },
+    {
+      "epoch": 0.0396134494049996,
+      "grad_norm": 0.5751525163650513,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1672,
+      "step": 31
+    },
+    {
+      "epoch": 0.040891302611612494,
+      "grad_norm": 0.5069852471351624,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1841,
+      "step": 32
+    },
+    {
+      "epoch": 0.04216915581822538,
+      "grad_norm": 0.41022780537605286,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1478,
+      "step": 33
+    },
+    {
+      "epoch": 0.04344700902483827,
+      "grad_norm": 0.38475725054740906,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.145,
+      "step": 34
+    },
+    {
+      "epoch": 0.04472486223145116,
+      "grad_norm": 0.373092919588089,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1286,
+      "step": 35
+    },
+    {
+      "epoch": 0.04600271543806405,
+      "grad_norm": 0.4084884822368622,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1228,
+      "step": 36
+    },
+    {
+      "epoch": 0.047280568644676946,
+      "grad_norm": 0.27328649163246155,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0774,
+      "step": 37
+    },
+    {
+      "epoch": 0.048558421851289835,
+      "grad_norm": 0.801368236541748,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4248,
+      "step": 38
+    },
+    {
+      "epoch": 0.049836275057902724,
+      "grad_norm": 0.6625673770904541,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4589,
+      "step": 39
+    },
+    {
+      "epoch": 0.05111412826451561,
+      "grad_norm": 0.5224865674972534,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3141,
+      "step": 40
+    },
+    {
+      "epoch": 0.0523919814711285,
+      "grad_norm": 0.43287745118141174,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2324,
+      "step": 41
+    },
+    {
+      "epoch": 0.0536698346777414,
+      "grad_norm": 0.5098556876182556,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2153,
+      "step": 42
+    },
+    {
+      "epoch": 0.054947687884354286,
+      "grad_norm": 0.3898968994617462,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1755,
+      "step": 43
+    },
+    {
+      "epoch": 0.056225541090967175,
+      "grad_norm": 0.42298492789268494,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2038,
+      "step": 44
+    },
+    {
+      "epoch": 0.057503394297580064,
+      "grad_norm": 0.3861464262008667,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1561,
+      "step": 45
+    },
+    {
+      "epoch": 0.05878124750419295,
+      "grad_norm": 0.47179993987083435,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1717,
+      "step": 46
+    },
+    {
+      "epoch": 0.06005910071080585,
+      "grad_norm": 0.46367916464805603,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1962,
+      "step": 47
+    },
+    {
+      "epoch": 0.06133695391741874,
+      "grad_norm": 0.4226861298084259,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1628,
+      "step": 48
+    },
+    {
+      "epoch": 0.06261480712403163,
+      "grad_norm": 0.2117103934288025,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0521,
+      "step": 49
+    },
+    {
+      "epoch": 0.06389266033064452,
+      "grad_norm": 0.3646078109741211,
+      "learning_rate": 0.0,
+      "loss": 0.0666,
+      "step": 50
+    },
+    {
+      "epoch": 0.06389266033064452,
+      "eval_loss": 0.22318783402442932,
+      "eval_runtime": 262.3219,
+      "eval_samples_per_second": 20.097,
+      "eval_steps_per_second": 2.512,
+      "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": 5.142948051031163e+17,
+  "total_flos": 1.0282699722976133e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null