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:b4fd3f83f2f11d408fa4ea6cd73c64fd2bc27aa24d97d0282b3f2cf6458f0be5
+oid sha256:9d58fb7f878b8aaefc339d2917fd63c7696672208362504432db785ce1e8be03
 size 116744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db8f49de1e892e6bf570aceb4db0f8502601f00a6a26c0cf3e19f5e1f13384e
+oid sha256:48992989b9a8453f704bbf4509cff339126391dbcee0882b20eb910d00fa6265
 size 243310

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0326dc0c045a1535138dd33dab752c44c92a8384f7287fdd763e31d92a3539
+oid sha256:2bac71987af3875bf88a9124b23fff7e84020eac552660256e187d1d723b5d21
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea92e447057aa0c1907b72e3042ae1aea00fe0403149d03f9bf8040d147eef3
+oid sha256:cd12f09d156f1fad4af159473e6c2411bf4b3c2eb51258ee372723dcc23b589d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d090c7f87e148276c976ee223c270accf90b819fc12b7e3bd8ba40ef768b90c7
+oid sha256:e1a3ae325f98bb00dfc42aa0de0bf6d149339bf35a2e838231abebec70741eb0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59753f79b7b1b49380c4682f879a50508ebe9a85f14ea17b0e4245aa98d86c29
+oid sha256:3a5f2492a7ec7da3f0333223e1b0b06ff898aa7f2e91afa46bf266c7e018d570
 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": 10.30517578125,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.015358034171626032,
+  "best_metric": 10.279115676879883,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.030716068343252065,
   "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": 1086.476,
       "eval_steps_per_second": 135.822,
       "step": 25
+    },
+    {
+      "epoch": 0.015972355538491072,
+      "grad_norm": 0.9604129195213318,
+      "learning_rate": 5e-05,
+      "loss": 10.2904,
+      "step": 26
+    },
+    {
+      "epoch": 0.016586676905356115,
+      "grad_norm": 0.9269930720329285,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.2859,
+      "step": 27
+    },
+    {
+      "epoch": 0.017200998272221157,
+      "grad_norm": 0.8787549734115601,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.2847,
+      "step": 28
+    },
+    {
+      "epoch": 0.017815319639086197,
+      "grad_norm": 0.8421987295150757,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.2891,
+      "step": 29
+    },
+    {
+      "epoch": 0.01842964100595124,
+      "grad_norm": 0.8014142513275146,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.2808,
+      "step": 30
+    },
+    {
+      "epoch": 0.01904396237281628,
+      "grad_norm": 0.8265954256057739,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.2778,
+      "step": 31
+    },
+    {
+      "epoch": 0.019658283739681322,
+      "grad_norm": 0.7673512697219849,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.2999,
+      "step": 32
+    },
+    {
+      "epoch": 0.02027260510654636,
+      "grad_norm": 0.7799116373062134,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.295,
+      "step": 33
+    },
+    {
+      "epoch": 0.020886926473411404,
+      "grad_norm": 0.7570932507514954,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.311,
+      "step": 34
+    },
+    {
+      "epoch": 0.021501247840276443,
+      "grad_norm": 0.7700633406639099,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3018,
+      "step": 35
+    },
+    {
+      "epoch": 0.022115569207141486,
+      "grad_norm": 0.7829461693763733,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.2994,
+      "step": 36
+    },
+    {
+      "epoch": 0.022729890574006525,
+      "grad_norm": 0.8024079203605652,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3168,
+      "step": 37
+    },
+    {
+      "epoch": 0.02334421194087157,
+      "grad_norm": 0.764173150062561,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3122,
+      "step": 38
+    },
+    {
+      "epoch": 0.02395853330773661,
+      "grad_norm": 0.9772190451622009,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.2755,
+      "step": 39
+    },
+    {
+      "epoch": 0.02457285467460165,
+      "grad_norm": 0.9249041676521301,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.2693,
+      "step": 40
+    },
+    {
+      "epoch": 0.025187176041466693,
+      "grad_norm": 0.8748021721839905,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.2821,
+      "step": 41
+    },
+    {
+      "epoch": 0.025801497408331733,
+      "grad_norm": 0.8471273183822632,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.2766,
+      "step": 42
+    },
+    {
+      "epoch": 0.026415818775196775,
+      "grad_norm": 0.8282643556594849,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.2786,
+      "step": 43
+    },
+    {
+      "epoch": 0.027030140142061815,
+      "grad_norm": 0.7962176203727722,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.2759,
+      "step": 44
+    },
+    {
+      "epoch": 0.027644461508926858,
+      "grad_norm": 0.7981472015380859,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.283,
+      "step": 45
+    },
+    {
+      "epoch": 0.028258782875791897,
+      "grad_norm": 0.800590991973877,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.2844,
+      "step": 46
+    },
+    {
+      "epoch": 0.02887310424265694,
+      "grad_norm": 0.7995105385780334,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.2902,
+      "step": 47
+    },
+    {
+      "epoch": 0.029487425609521983,
+      "grad_norm": 0.8139747381210327,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.299,
+      "step": 48
+    },
+    {
+      "epoch": 0.030101746976387022,
+      "grad_norm": 0.7791361808776855,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3037,
+      "step": 49
+    },
+    {
+      "epoch": 0.030716068343252065,
+      "grad_norm": 0.7885679602622986,
+      "learning_rate": 0.0,
+      "loss": 10.3219,
+      "step": 50
+    },
+    {
+      "epoch": 0.030716068343252065,
+      "eval_loss": 10.279115676879883,
+      "eval_runtime": 10.1008,
+      "eval_samples_per_second": 1085.753,
+      "eval_steps_per_second": 135.732,
+      "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": 42311303823360.0,
+  "total_flos": 84596179599360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null