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:e94b5cc31d062555aa134f217b3556b47d866bdc8f33704b7898113767be5ca9
+oid sha256:1366ac44ffac12a0a482cc75b9af62568d1d4527b5b1376201b421b0cf54db35
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351f5fdc24e989f2cf3739641e3dd1592f7be85f6e945777711cb8e36a463b47
+oid sha256:921bf1fa415918585362988aa2a66a996265afd26613ee9115ef43865725baec
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86939f697a67881b896b4a1db3dd9ce452e9ec835e5ee1794c12b648284748e1
+oid sha256:d24b04228f3416d447bf0a8cc57e9443e8f765458d18e6a061547ff25da34bd8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5e736eed0d7bf8f08550b305dace922349fcd6a61b22a92488854e4616b73d
+oid sha256:65c40c6fec9640d9ed8c0a7c2c75df6bd044d8043d2830866b17d3dd812a5544
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec3af60a473baea43eb54bc1d5a8ec26b8c5d22a94f9f404f1b8acc0fc161a3
+oid sha256:6037f5814f76f53317813e1f4149d237b326b3fc774d6d98f8872079e16ff4bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3520f19d06886c1056d4a102e7733fc2606fbbb83126641ab465c51e6d732c3b
+oid sha256:cd86f2267af6b9e3401251f8c483a8c524fda5965c5d025d00ec14d7daf9ad64
 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": 0.3402710258960724,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0844059928254906,
+  "best_metric": 0.1907738745212555,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1688119856509812,
   "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": 36.326,
       "eval_steps_per_second": 4.552,
       "step": 25
+    },
+    {
+      "epoch": 0.08778223253851024,
+      "grad_norm": 3.0682921409606934,
+      "learning_rate": 5e-05,
+      "loss": 0.4922,
+      "step": 26
+    },
+    {
+      "epoch": 0.09115847225152986,
+      "grad_norm": 2.6181204319000244,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3891,
+      "step": 27
+    },
+    {
+      "epoch": 0.09453471196454949,
+      "grad_norm": 2.052562713623047,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.264,
+      "step": 28
+    },
+    {
+      "epoch": 0.09791095167756911,
+      "grad_norm": 1.5420339107513428,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1613,
+      "step": 29
+    },
+    {
+      "epoch": 0.10128719139058873,
+      "grad_norm": 3.7188830375671387,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2916,
+      "step": 30
+    },
+    {
+      "epoch": 0.10466343110360836,
+      "grad_norm": 3.411963939666748,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3516,
+      "step": 31
+    },
+    {
+      "epoch": 0.10803967081662798,
+      "grad_norm": 11.465725898742676,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2923,
+      "step": 32
+    },
+    {
+      "epoch": 0.11141591052964761,
+      "grad_norm": 5.158927917480469,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5667,
+      "step": 33
+    },
+    {
+      "epoch": 0.11479215024266723,
+      "grad_norm": 0.8077765703201294,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0768,
+      "step": 34
+    },
+    {
+      "epoch": 0.11816838995568685,
+      "grad_norm": 1.4526370763778687,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1387,
+      "step": 35
+    },
+    {
+      "epoch": 0.12154462966870648,
+      "grad_norm": 3.2545902729034424,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3294,
+      "step": 36
+    },
+    {
+      "epoch": 0.1249208693817261,
+      "grad_norm": 1.122367024421692,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1178,
+      "step": 37
+    },
+    {
+      "epoch": 0.12829710909474573,
+      "grad_norm": 1.5557242631912231,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2367,
+      "step": 38
+    },
+    {
+      "epoch": 0.13167334880776535,
+      "grad_norm": 1.4077110290527344,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2404,
+      "step": 39
+    },
+    {
+      "epoch": 0.13504958852078497,
+      "grad_norm": 1.0390076637268066,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1126,
+      "step": 40
+    },
+    {
+      "epoch": 0.1384258282338046,
+      "grad_norm": 0.6616483330726624,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0689,
+      "step": 41
+    },
+    {
+      "epoch": 0.14180206794682423,
+      "grad_norm": 0.7459376454353333,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0661,
+      "step": 42
+    },
+    {
+      "epoch": 0.14517830765984385,
+      "grad_norm": 1.7347726821899414,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2198,
+      "step": 43
+    },
+    {
+      "epoch": 0.14855454737286347,
+      "grad_norm": 1.3913830518722534,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.115,
+      "step": 44
+    },
+    {
+      "epoch": 0.1519307870858831,
+      "grad_norm": 5.454977989196777,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7133,
+      "step": 45
+    },
+    {
+      "epoch": 0.1553070267989027,
+      "grad_norm": 1.3282166719436646,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0953,
+      "step": 46
+    },
+    {
+      "epoch": 0.15868326651192236,
+      "grad_norm": 0.687819242477417,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0587,
+      "step": 47
+    },
+    {
+      "epoch": 0.16205950622494197,
+      "grad_norm": 0.6925812363624573,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1267,
+      "step": 48
+    },
+    {
+      "epoch": 0.1654357459379616,
+      "grad_norm": 1.8676002025604248,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1939,
+      "step": 49
+    },
+    {
+      "epoch": 0.1688119856509812,
+      "grad_norm": 0.3576854169368744,
+      "learning_rate": 0.0,
+      "loss": 0.0117,
+      "step": 50
+    },
+    {
+      "epoch": 0.1688119856509812,
+      "eval_loss": 0.1907738745212555,
+      "eval_runtime": 54.784,
+      "eval_samples_per_second": 36.416,
+      "eval_steps_per_second": 4.563,
+      "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