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:dd5a294233137afd57c5ed660fa6d78b7af8c41be056407910c731b8e0f0a127
+oid sha256:30b1197f8c001e648cc21c3a2f52b5b9ab5847d7e3faf96a98c982ef353d7c3d
 size 116744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a463145837ff8d6dff6c1332858a701b1ecac33f6add431ac0c6fc7b0535a16
+oid sha256:cbc360a986d0eff8fdd066b9cb6c6d86407649747baf0e222099d0f9c1f7ca1e
 size 243310

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00fc8851caea59b377b886d5927622e9a6688f7552cd8677ef4f47577f5a4f2b
+oid sha256:f711d6320cc2a93c650d6d729c8971d0d773b8cb171c5051d93708acc92dd09a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fce8d26d3606c454b2a7fc6bfd4a0c8c41a6a61524b11b424de1496ccc3bea
+oid sha256:e55d5b446e9b4b532831f55f45365216765b37b2e45bc9fff9db5e2344a3754c
 size 14512

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": 10.368788719177246,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0327653997378768,
+  "best_metric": 10.364721298217773,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0655307994757536,
   "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": 357.442,
       "eval_steps_per_second": 89.395,
       "step": 25
+    },
+    {
+      "epoch": 0.03407601572739188,
+      "grad_norm": 0.14859028160572052,
+      "learning_rate": 5e-05,
+      "loss": 10.3677,
+      "step": 26
+    },
+    {
+      "epoch": 0.035386631716906945,
+      "grad_norm": 0.14715676009655,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3674,
+      "step": 27
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 0.1489713191986084,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.369,
+      "step": 28
+    },
+    {
+      "epoch": 0.03800786369593709,
+      "grad_norm": 0.15279723703861237,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3671,
+      "step": 29
+    },
+    {
+      "epoch": 0.039318479685452164,
+      "grad_norm": 0.14576803147792816,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3687,
+      "step": 30
+    },
+    {
+      "epoch": 0.04062909567496723,
+      "grad_norm": 0.1643356829881668,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3666,
+      "step": 31
+    },
+    {
+      "epoch": 0.04193971166448231,
+      "grad_norm": 0.15099547803401947,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3666,
+      "step": 32
+    },
+    {
+      "epoch": 0.04325032765399738,
+      "grad_norm": 0.1730622947216034,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3648,
+      "step": 33
+    },
+    {
+      "epoch": 0.04456094364351245,
+      "grad_norm": 0.15695245563983917,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.366,
+      "step": 34
+    },
+    {
+      "epoch": 0.045871559633027525,
+      "grad_norm": 0.1533222794532776,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3665,
+      "step": 35
+    },
+    {
+      "epoch": 0.047182175622542594,
+      "grad_norm": 0.1350749284029007,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.366,
+      "step": 36
+    },
+    {
+      "epoch": 0.04849279161205767,
+      "grad_norm": 0.1510956883430481,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3639,
+      "step": 37
+    },
+    {
+      "epoch": 0.04980340760157274,
+      "grad_norm": 0.15642888844013214,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3667,
+      "step": 38
+    },
+    {
+      "epoch": 0.05111402359108781,
+      "grad_norm": 0.17887574434280396,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3621,
+      "step": 39
+    },
+    {
+      "epoch": 0.05242463958060288,
+      "grad_norm": 0.17263266444206238,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3623,
+      "step": 40
+    },
+    {
+      "epoch": 0.053735255570117955,
+      "grad_norm": 0.15901875495910645,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3657,
+      "step": 41
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 0.1725824922323227,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3687,
+      "step": 42
+    },
+    {
+      "epoch": 0.0563564875491481,
+      "grad_norm": 0.17225879430770874,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3635,
+      "step": 43
+    },
+    {
+      "epoch": 0.057667103538663174,
+      "grad_norm": 0.19542855024337769,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3608,
+      "step": 44
+    },
+    {
+      "epoch": 0.05897771952817824,
+      "grad_norm": 0.16884516179561615,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3693,
+      "step": 45
+    },
+    {
+      "epoch": 0.06028833551769332,
+      "grad_norm": 0.19233977794647217,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3623,
+      "step": 46
+    },
+    {
+      "epoch": 0.061598951507208385,
+      "grad_norm": 0.204484760761261,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3616,
+      "step": 47
+    },
+    {
+      "epoch": 0.06290956749672345,
+      "grad_norm": 0.23938828706741333,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3619,
+      "step": 48
+    },
+    {
+      "epoch": 0.06422018348623854,
+      "grad_norm": 0.2926636338233948,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.364,
+      "step": 49
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "grad_norm": 0.3798704445362091,
+      "learning_rate": 0.0,
+      "loss": 10.3716,
+      "step": 50
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "eval_loss": 10.364721298217773,
+      "eval_runtime": 7.1814,
+      "eval_samples_per_second": 358.006,
+      "eval_steps_per_second": 89.536,
+      "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": 21142437888000.0,
+  "total_flos": 42284875776000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null