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:a410ce79068e03006652d778bc565a79a7111cd7d96db8a59af8bae079e23723
+oid sha256:c5b3aa80294e1b4d4a02cddb1f8a5bb2832420ebe582d8cd26a11dc09d45b70e
 size 113864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cfc296790b456ff93ed5ed6dae205667c0fa20dbb8e2d67cb88618608f5db02
+oid sha256:64e1452ff09f40707db9993823990a6a06493b023fe842af000f05f289da46fa
 size 244554

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3bc0d052fa0c40cb49606b8b76c5e8cf215cba0d1012e161054b9b5604bd0e5
+oid sha256:16de897643c04256357a2ae8bd22b63f0a399e5b4afe3a8ab3b30fab679eac9f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd3cf191ec4bf578488f08809d5b32ef010d8be0b62a5546fee33e9467f7acc
+oid sha256:df6a8b33a2e993a4cc66b6f9e599598964e4be4ce000c2a12ee33ec71565b376
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998f9fada6dc7fa908fdb58ada33b50b316397a1b20a06dcbff7bfb44597aca5
+oid sha256:d407c183366b1f2551ac6295b23cdfce58d37251332669ea65d3623393cea72f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e4d0be191dd72ea2132929229c2b5a344646f448bc236c56bad650983d1062
+oid sha256:8c72c402ad43ac7bb35a27621c5d4a92d39d0ca967d23aaf1cba65b7397b97ac
 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": 10.36552906036377,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05557099194220617,
+  "best_metric": 10.361546516418457,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11114198388441233,
   "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": 835.19,
       "eval_steps_per_second": 104.433,
       "step": 25
+    },
+    {
+      "epoch": 0.05779383161989442,
+      "grad_norm": 2.962451934814453,
+      "learning_rate": 5e-05,
+      "loss": 165.8313,
+      "step": 26
+    },
+    {
+      "epoch": 0.06001667129758266,
+      "grad_norm": 2.890627861022949,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 165.8857,
+      "step": 27
+    },
+    {
+      "epoch": 0.06223951097527091,
+      "grad_norm": 2.9866206645965576,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 165.8528,
+      "step": 28
+    },
+    {
+      "epoch": 0.06446235065295916,
+      "grad_norm": 3.124624729156494,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 165.83,
+      "step": 29
+    },
+    {
+      "epoch": 0.0666851903306474,
+      "grad_norm": 3.122779130935669,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 165.8347,
+      "step": 30
+    },
+    {
+      "epoch": 0.06890803000833565,
+      "grad_norm": 3.268548011779785,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 165.8374,
+      "step": 31
+    },
+    {
+      "epoch": 0.07113086968602389,
+      "grad_norm": 3.225985527038574,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 165.8352,
+      "step": 32
+    },
+    {
+      "epoch": 0.07335370936371215,
+      "grad_norm": 3.189636468887329,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 165.8356,
+      "step": 33
+    },
+    {
+      "epoch": 0.07557654904140039,
+      "grad_norm": 3.24165678024292,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 165.8257,
+      "step": 34
+    },
+    {
+      "epoch": 0.07779938871908863,
+      "grad_norm": 3.156804323196411,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 165.7957,
+      "step": 35
+    },
+    {
+      "epoch": 0.08002222839677688,
+      "grad_norm": 3.0788278579711914,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 165.7892,
+      "step": 36
+    },
+    {
+      "epoch": 0.08224506807446513,
+      "grad_norm": 2.8068950176239014,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 165.7598,
+      "step": 37
+    },
+    {
+      "epoch": 0.08446790775215338,
+      "grad_norm": 2.9427618980407715,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 165.7805,
+      "step": 38
+    },
+    {
+      "epoch": 0.08669074742984162,
+      "grad_norm": 2.909614086151123,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 165.8167,
+      "step": 39
+    },
+    {
+      "epoch": 0.08891358710752988,
+      "grad_norm": 3.3619277477264404,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 165.8043,
+      "step": 40
+    },
+    {
+      "epoch": 0.09113642678521812,
+      "grad_norm": 3.4324169158935547,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 165.7733,
+      "step": 41
+    },
+    {
+      "epoch": 0.09335926646290636,
+      "grad_norm": 3.487154245376587,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 165.791,
+      "step": 42
+    },
+    {
+      "epoch": 0.0955821061405946,
+      "grad_norm": 3.343712329864502,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 165.7748,
+      "step": 43
+    },
+    {
+      "epoch": 0.09780494581828286,
+      "grad_norm": 3.2424018383026123,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 165.8362,
+      "step": 44
+    },
+    {
+      "epoch": 0.1000277854959711,
+      "grad_norm": 3.2945828437805176,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 165.8215,
+      "step": 45
+    },
+    {
+      "epoch": 0.10225062517365935,
+      "grad_norm": 3.2656757831573486,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 165.7962,
+      "step": 46
+    },
+    {
+      "epoch": 0.10447346485134759,
+      "grad_norm": 3.435271978378296,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 165.774,
+      "step": 47
+    },
+    {
+      "epoch": 0.10669630452903585,
+      "grad_norm": 3.346522808074951,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 165.7944,
+      "step": 48
+    },
+    {
+      "epoch": 0.10891914420672409,
+      "grad_norm": 3.1068100929260254,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 165.7602,
+      "step": 49
+    },
+    {
+      "epoch": 0.11114198388441233,
+      "grad_norm": 3.231125593185425,
+      "learning_rate": 0.0,
+      "loss": 165.7337,
+      "step": 50
+    },
+    {
+      "epoch": 0.11114198388441233,
+      "eval_loss": 10.361546516418457,
+      "eval_runtime": 3.6259,
+      "eval_samples_per_second": 835.92,
+      "eval_steps_per_second": 104.525,
+      "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": 43866355924992.0,
+  "total_flos": 87601845633024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null