Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c9005fb6bb9bc77268f31058326a9e94964ba7e596f3832dfd62c9430c0c32
+oid sha256:3ea16d52331b9a2bfc14453c176a9da68b4c86b277572e97b4514d6324a45fc8
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a3a70dca4e3ec4a0425bb12fa9a53a57e64c9b33f741803740893ace303a1c
+oid sha256:2b14b282198acbda899f3a59a19f98ab4deb2821174fa52d8f65924cf6d7522b
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5f099f97beef2b60fcec305130b5059eb6d19d755929dad7d82499bd744a1e
+oid sha256:e52a2f59cb086f30ce809bf5b8aeeb0343ad734864d1a23c040e7a48d7e929e7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac85736b34a2ee66df98bc4d9584041519cb5d96ac22891a25ed548190a32dd
+oid sha256:1da5b92b6341350ab7d8e7eb54e0e0751544a343c4e651435c1b4e28ee3c7ab7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f16bf10550768a69437774f9e88f88e34cdd94e8ce03e7675b448e8aa421632a
+oid sha256:043ce6a0270306722ba7ddc5b55e07765df4bded7d4defc330ee320ebc4ffe86
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bae50a535c26f431bd51e7f305306679a294bad5b0614b873bbd68de3fab608
+oid sha256:63b8866b373aedbc68eeaab753c5a94c3817d6c831a852437b3045a636ea8529
 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": 2.0811705589294434,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004537205081669692,
+  "best_metric": 1.948492407798767,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009074410163339383,
   "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": 126.839,
       "eval_steps_per_second": 15.855,
       "step": 25
+    },
+    {
+      "epoch": 0.004718693284936479,
+      "grad_norm": 3.760965347290039,
+      "learning_rate": 5e-05,
+      "loss": 2.2076,
+      "step": 26
+    },
+    {
+      "epoch": 0.004900181488203267,
+      "grad_norm": 3.1969687938690186,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.1796,
+      "step": 27
+    },
+    {
+      "epoch": 0.005081669691470054,
+      "grad_norm": 2.2780795097351074,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1283,
+      "step": 28
+    },
+    {
+      "epoch": 0.005263157894736842,
+      "grad_norm": 1.1522444486618042,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0666,
+      "step": 29
+    },
+    {
+      "epoch": 0.0054446460980036296,
+      "grad_norm": 1.082772135734558,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.0371,
+      "step": 30
+    },
+    {
+      "epoch": 0.005626134301270417,
+      "grad_norm": 1.2637733221054077,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.0485,
+      "step": 31
+    },
+    {
+      "epoch": 0.005807622504537205,
+      "grad_norm": 1.3118598461151123,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0443,
+      "step": 32
+    },
+    {
+      "epoch": 0.005989110707803993,
+      "grad_norm": 1.468990445137024,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.0406,
+      "step": 33
+    },
+    {
+      "epoch": 0.006170598911070781,
+      "grad_norm": 1.9433963298797607,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0127,
+      "step": 34
+    },
+    {
+      "epoch": 0.006352087114337568,
+      "grad_norm": 2.6556968688964844,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.9951,
+      "step": 35
+    },
+    {
+      "epoch": 0.006533575317604356,
+      "grad_norm": 3.3726489543914795,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.9365,
+      "step": 36
+    },
+    {
+      "epoch": 0.006715063520871143,
+      "grad_norm": 3.5065298080444336,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8667,
+      "step": 37
+    },
+    {
+      "epoch": 0.006896551724137931,
+      "grad_norm": 1.196144938468933,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0148,
+      "step": 38
+    },
+    {
+      "epoch": 0.0070780399274047185,
+      "grad_norm": 0.8093488812446594,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.0359,
+      "step": 39
+    },
+    {
+      "epoch": 0.007259528130671506,
+      "grad_norm": 0.8119086027145386,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0408,
+      "step": 40
+    },
+    {
+      "epoch": 0.007441016333938294,
+      "grad_norm": 0.7345393896102905,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.0226,
+      "step": 41
+    },
+    {
+      "epoch": 0.007622504537205082,
+      "grad_norm": 0.7744444608688354,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.0291,
+      "step": 42
+    },
+    {
+      "epoch": 0.00780399274047187,
+      "grad_norm": 0.8714845776557922,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0369,
+      "step": 43
+    },
+    {
+      "epoch": 0.007985480943738656,
+      "grad_norm": 0.8915154933929443,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0011,
+      "step": 44
+    },
+    {
+      "epoch": 0.008166969147005444,
+      "grad_norm": 1.016900658607483,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0137,
+      "step": 45
+    },
+    {
+      "epoch": 0.008348457350272231,
+      "grad_norm": 1.1873092651367188,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9655,
+      "step": 46
+    },
+    {
+      "epoch": 0.00852994555353902,
+      "grad_norm": 1.1978569030761719,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.9304,
+      "step": 47
+    },
+    {
+      "epoch": 0.008711433756805808,
+      "grad_norm": 1.3368781805038452,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8544,
+      "step": 48
+    },
+    {
+      "epoch": 0.008892921960072596,
+      "grad_norm": 1.2073959112167358,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7718,
+      "step": 49
+    },
+    {
+      "epoch": 0.009074410163339383,
+      "grad_norm": 3.517503499984741,
+      "learning_rate": 0.0,
+      "loss": 1.7169,
+      "step": 50
+    },
+    {
+      "epoch": 0.009074410163339383,
+      "eval_loss": 1.948492407798767,
+      "eval_runtime": 292.5856,
+      "eval_samples_per_second": 126.869,
+      "eval_steps_per_second": 15.859,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null