Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:027b306ccf8db6367ebcf49dc092c0512309040f5aceda29eef65201056833cc
+oid sha256:7c3beac17a389072cf980c699395fee14ce4c863c04992e33a9f31416571fbf2
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce5c3a992f3e7f4f20d21e9ed56a7ce1294d684698fd5d2381ec8696ffc4be7
+oid sha256:c90d40b1f6b2c991384aeb0af0160d8ee3179aab47af5120cc6babdb628cf1e8
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa169d24658e6975ad4b18ca2a39d04528bf18b7e82c79fbb36f6df58a1f49ef
+oid sha256:1aa906bf3ba944d0a89923bb453e477b1672c949313fd57493fe6272778f02ef
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e36a5380ee5dbd1ab89edeb8ac840e8563d22d3b3467919b5e14cd21ae567f65
+oid sha256:344135d1e73d8ffc4d1dae69a65b4de0797242dfa9a9e77602a3a476bbacb86c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffe13f95730ad0280fae775205c51ad1f2487d76e6c446c36ddbfee4f5170c4
+oid sha256:6eab8cd7fc893207087765285e4dc97caf4b301e43d5bd3f0f9c3fec8e80163c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb7583ab73f637111780eda6c198b8889e40c32f3016c5e11ae6d4372d26b76
+oid sha256:ecbe80fcf4bde57801d88add7f0b4576a05d2c30c9d3b155d9f3f6f70f39a095
 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": 1.1579746007919312,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.027934911655841888,
+  "best_metric": 1.124672293663025,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.055869823311683775,
   "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": 23.121,
       "eval_steps_per_second": 2.892,
       "step": 25
+    },
+    {
+      "epoch": 0.029052308122075564,
+      "grad_norm": 7.1438422203063965,
+      "learning_rate": 5e-05,
+      "loss": 1.137,
+      "step": 26
+    },
+    {
+      "epoch": 0.03016970458830924,
+      "grad_norm": 4.9483513832092285,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2287,
+      "step": 27
+    },
+    {
+      "epoch": 0.031287101054542917,
+      "grad_norm": 22.43474769592285,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.88,
+      "step": 28
+    },
+    {
+      "epoch": 0.03240449752077659,
+      "grad_norm": 6.235660076141357,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9989,
+      "step": 29
+    },
+    {
+      "epoch": 0.03352189398701027,
+      "grad_norm": 3.5960636138916016,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0437,
+      "step": 30
+    },
+    {
+      "epoch": 0.03463929045324394,
+      "grad_norm": 3.158735513687134,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9847,
+      "step": 31
+    },
+    {
+      "epoch": 0.035756686919477615,
+      "grad_norm": 3.074357748031616,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0664,
+      "step": 32
+    },
+    {
+      "epoch": 0.03687408338571129,
+      "grad_norm": 3.6634132862091064,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0598,
+      "step": 33
+    },
+    {
+      "epoch": 0.03799147985194497,
+      "grad_norm": 3.828514814376831,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0811,
+      "step": 34
+    },
+    {
+      "epoch": 0.039108876318178644,
+      "grad_norm": 5.093250274658203,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1799,
+      "step": 35
+    },
+    {
+      "epoch": 0.04022627278441232,
+      "grad_norm": 5.567080974578857,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1715,
+      "step": 36
+    },
+    {
+      "epoch": 0.041343669250646,
+      "grad_norm": 6.227445125579834,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2163,
+      "step": 37
+    },
+    {
+      "epoch": 0.04246106571687967,
+      "grad_norm": 15.248550415039062,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2217,
+      "step": 38
+    },
+    {
+      "epoch": 0.04357846218311335,
+      "grad_norm": 3.6309807300567627,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1938,
+      "step": 39
+    },
+    {
+      "epoch": 0.04469585864934702,
+      "grad_norm": 5.848428249359131,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.2074,
+      "step": 40
+    },
+    {
+      "epoch": 0.045813255115580695,
+      "grad_norm": 17.644390106201172,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5582,
+      "step": 41
+    },
+    {
+      "epoch": 0.04693065158181437,
+      "grad_norm": 3.6176645755767822,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0027,
+      "step": 42
+    },
+    {
+      "epoch": 0.04804804804804805,
+      "grad_norm": 3.052868127822876,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9873,
+      "step": 43
+    },
+    {
+      "epoch": 0.049165444514281724,
+      "grad_norm": 3.1431257724761963,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9985,
+      "step": 44
+    },
+    {
+      "epoch": 0.0502828409805154,
+      "grad_norm": 3.236440896987915,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0187,
+      "step": 45
+    },
+    {
+      "epoch": 0.05140023744674908,
+      "grad_norm": 3.378023624420166,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0547,
+      "step": 46
+    },
+    {
+      "epoch": 0.05251763391298275,
+      "grad_norm": 3.970024585723877,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1256,
+      "step": 47
+    },
+    {
+      "epoch": 0.05363503037921642,
+      "grad_norm": 5.147023677825928,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1864,
+      "step": 48
+    },
+    {
+      "epoch": 0.0547524268454501,
+      "grad_norm": 7.185994625091553,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1914,
+      "step": 49
+    },
+    {
+      "epoch": 0.055869823311683775,
+      "grad_norm": 13.471297264099121,
+      "learning_rate": 0.0,
+      "loss": 1.3024,
+      "step": 50
+    },
+    {
+      "epoch": 0.055869823311683775,
+      "eval_loss": 1.124672293663025,
+      "eval_runtime": 261.2973,
+      "eval_samples_per_second": 23.073,
+      "eval_steps_per_second": 2.886,
+      "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": 6.061186562916352e+16,
+  "total_flos": 1.2007152964285235e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null