Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:186038c66bc66d8181f8f4d1f11908619adbdd7124d48c7142005fb7923f7909
+oid sha256:6db1b4e6cd3b0eb517ed0f7279d55347ab17b8855190c1d8e961c182b82377ef
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e47ebc38d3fa5d7082a6f47400c4f65e5d7e5479d655321deb52b94f5820da6
+oid sha256:037cb3be0ca832339065309f7dfd4b30a3c839a305d8d1a15a440297c498f35e
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec351513ae5b6d7d98d0318260b615bf88558aadd1edb56ca721272a058cd194
+oid sha256:f92c05c4f18e6445f874587be77bfb43caf675600ffb460ff4732c05fca03966
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbecc89e227d4ac6e93217c0e8b9585ae0c88ff3afb1387f2aec643984f50254
+oid sha256:3f206020b45cacf4cb12c7983ded47157adb5783c73facb77d6205cf5f10fe22
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d41af9b09009a8731177bfe46ed4ee5c7e709c8f9885cc36f93a1a3f369e39d7
+oid sha256:eedf610d0b6adc8f76972389eee74b330c0fc7d6a3d9ef615d0c5a4df71e298b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3513178b409917686799fa0ac4ef6fbce8adc7edda6186bfe0f62d48b629cd04
+oid sha256:66daaac8087d791c7c603b3562f55c33736bc57b91550e7ff2e2f29b2343d427
 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": 10.86867904663086,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4975124378109453,
+  "best_metric": 10.796202659606934,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.9950248756218906,
   "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": 300.843,
       "eval_steps_per_second": 38.16,
       "step": 25
+    },
+    {
+      "epoch": 0.5174129353233831,
+      "grad_norm": 12.870345115661621,
+      "learning_rate": 5e-05,
+      "loss": 10.8808,
+      "step": 26
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "grad_norm": 13.499300003051758,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.871,
+      "step": 27
+    },
+    {
+      "epoch": 0.5572139303482587,
+      "grad_norm": 12.799941062927246,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.8572,
+      "step": 28
+    },
+    {
+      "epoch": 0.5771144278606966,
+      "grad_norm": 12.39841365814209,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.8524,
+      "step": 29
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 13.075429916381836,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.838,
+      "step": 30
+    },
+    {
+      "epoch": 0.6169154228855721,
+      "grad_norm": 12.90629768371582,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.8383,
+      "step": 31
+    },
+    {
+      "epoch": 0.6368159203980099,
+      "grad_norm": 12.80428695678711,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.8326,
+      "step": 32
+    },
+    {
+      "epoch": 0.6567164179104478,
+      "grad_norm": 12.830976486206055,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.826,
+      "step": 33
+    },
+    {
+      "epoch": 0.6766169154228856,
+      "grad_norm": 12.864173889160156,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.8366,
+      "step": 34
+    },
+    {
+      "epoch": 0.6965174129353234,
+      "grad_norm": 13.161463737487793,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.8123,
+      "step": 35
+    },
+    {
+      "epoch": 0.7164179104477612,
+      "grad_norm": 13.65135383605957,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.8064,
+      "step": 36
+    },
+    {
+      "epoch": 0.736318407960199,
+      "grad_norm": 13.233158111572266,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.824,
+      "step": 37
+    },
+    {
+      "epoch": 0.7562189054726368,
+      "grad_norm": 12.842829704284668,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.8049,
+      "step": 38
+    },
+    {
+      "epoch": 0.7761194029850746,
+      "grad_norm": 12.31116008758545,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.813,
+      "step": 39
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "grad_norm": 12.684613227844238,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.8142,
+      "step": 40
+    },
+    {
+      "epoch": 0.8159203980099502,
+      "grad_norm": 12.409058570861816,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.812,
+      "step": 41
+    },
+    {
+      "epoch": 0.835820895522388,
+      "grad_norm": 12.554705619812012,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.8103,
+      "step": 42
+    },
+    {
+      "epoch": 0.8557213930348259,
+      "grad_norm": 12.32496166229248,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.8091,
+      "step": 43
+    },
+    {
+      "epoch": 0.8756218905472637,
+      "grad_norm": 12.167740821838379,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.8085,
+      "step": 44
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 12.719805717468262,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.7878,
+      "step": 45
+    },
+    {
+      "epoch": 0.9154228855721394,
+      "grad_norm": 12.949674606323242,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.801,
+      "step": 46
+    },
+    {
+      "epoch": 0.9353233830845771,
+      "grad_norm": 12.62083911895752,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.7977,
+      "step": 47
+    },
+    {
+      "epoch": 0.9552238805970149,
+      "grad_norm": 13.022436141967773,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.7873,
+      "step": 48
+    },
+    {
+      "epoch": 0.9751243781094527,
+      "grad_norm": 13.229351043701172,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.7899,
+      "step": 49
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 14.39165210723877,
+      "learning_rate": 0.0,
+      "loss": 10.8008,
+      "step": 50
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "eval_loss": 10.796202659606934,
+      "eval_runtime": 1.1439,
+      "eval_samples_per_second": 296.349,
+      "eval_steps_per_second": 37.59,
+      "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