Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0c4d2e6e604244fcc49be5a2d544b696554077baff5e242a886a9a7e041fcf
+oid sha256:253268780f301c471303fee466d1b60008a962b24fbad41c4ef897d0aeb60bdd
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb33d0a14cff3e084fbbc7750a4181734335e3bcb71e078b14a9ab198e79b03b
+oid sha256:304653f7438d5d0dd1e84ad2c8b6f12b074c90b9ce1ee5a0ba570b3a9243d556
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d8c94bf1fa58231e88b8170fff2de1ad20f82bb80696c7d69a8b551bdad486
+oid sha256:f2ae9aa2319d9f753dfebd9c383274aca7a410b23ba4415fe33f6d63412c894c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a8d8bcad42b4e06bfe1d9d2ff4091094899e934643414b45e8c4673b2fd058
+oid sha256:346c67be8a083e986a572afbebdcfcc71085f276e95df8dded4b0fa155e86b6e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fde17f6aa9dc34cd68609f90433a0cfdbc9ea421eebf33a2e328f6c3cbeaff8
+oid sha256:e61d8be8c09341ca5151063fe71fa0e00579fe8561714703c97ed54c894de1d7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:287fecb8fe0eef4c51ab89ad13f4241ed38ef48f91fc946ca4f953dd1909ed8e
+oid sha256:6b659b908ba7a25cbd0044aa765152593be6c1512f8045608543fbb15e855cb5
 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": 2.830770969390869,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010379365820748353,
+  "best_metric": 0.5452532172203064,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.020758731641496705,
   "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": 41.689,
       "eval_steps_per_second": 5.213,
       "step": 25
+    },
+    {
+      "epoch": 0.010794540453578286,
+      "grad_norm": 90.39044189453125,
+      "learning_rate": 5e-05,
+      "loss": 41.3358,
+      "step": 26
+    },
+    {
+      "epoch": 0.011209715086408221,
+      "grad_norm": 107.48399353027344,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 37.8233,
+      "step": 27
+    },
+    {
+      "epoch": 0.011624889719238155,
+      "grad_norm": 123.58059692382812,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 36.4973,
+      "step": 28
+    },
+    {
+      "epoch": 0.012040064352068088,
+      "grad_norm": 146.50843811035156,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 34.2894,
+      "step": 29
+    },
+    {
+      "epoch": 0.012455238984898023,
+      "grad_norm": 161.9147186279297,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 32.1584,
+      "step": 30
+    },
+    {
+      "epoch": 0.012870413617727956,
+      "grad_norm": 189.58154296875,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 30.0903,
+      "step": 31
+    },
+    {
+      "epoch": 0.013285588250557891,
+      "grad_norm": 216.47386169433594,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 28.0404,
+      "step": 32
+    },
+    {
+      "epoch": 0.013700762883387825,
+      "grad_norm": 251.19036865234375,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 25.0547,
+      "step": 33
+    },
+    {
+      "epoch": 0.01411593751621776,
+      "grad_norm": 284.711181640625,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 22.4096,
+      "step": 34
+    },
+    {
+      "epoch": 0.014531112149047693,
+      "grad_norm": 316.04901123046875,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 19.3858,
+      "step": 35
+    },
+    {
+      "epoch": 0.014946286781877626,
+      "grad_norm": 348.51702880859375,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 16.01,
+      "step": 36
+    },
+    {
+      "epoch": 0.015361461414707562,
+      "grad_norm": 656.499267578125,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 50.5854,
+      "step": 37
+    },
+    {
+      "epoch": 0.015776636047537495,
+      "grad_norm": 539.625244140625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 39.0507,
+      "step": 38
+    },
+    {
+      "epoch": 0.01619181068036743,
+      "grad_norm": 329.3690490722656,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 9.2602,
+      "step": 39
+    },
+    {
+      "epoch": 0.016606985313197365,
+      "grad_norm": 228.13270568847656,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 6.9433,
+      "step": 40
+    },
+    {
+      "epoch": 0.017022159946027297,
+      "grad_norm": 169.77978515625,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 6.0569,
+      "step": 41
+    },
+    {
+      "epoch": 0.017437334578857232,
+      "grad_norm": 143.93309020996094,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.7341,
+      "step": 42
+    },
+    {
+      "epoch": 0.017852509211687167,
+      "grad_norm": 102.2474136352539,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.0804,
+      "step": 43
+    },
+    {
+      "epoch": 0.0182676838445171,
+      "grad_norm": 81.61624908447266,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.1245,
+      "step": 44
+    },
+    {
+      "epoch": 0.018682858477347034,
+      "grad_norm": 69.04170989990234,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 5.4536,
+      "step": 45
+    },
+    {
+      "epoch": 0.01909803311017697,
+      "grad_norm": 60.76116180419922,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 5.0234,
+      "step": 46
+    },
+    {
+      "epoch": 0.019513207743006904,
+      "grad_norm": 45.23762130737305,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.7514,
+      "step": 47
+    },
+    {
+      "epoch": 0.019928382375836835,
+      "grad_norm": 62.682037353515625,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.2911,
+      "step": 48
+    },
+    {
+      "epoch": 0.02034355700866677,
+      "grad_norm": 132.07171630859375,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 9.7136,
+      "step": 49
+    },
+    {
+      "epoch": 0.020758731641496705,
+      "grad_norm": 744.1082153320312,
+      "learning_rate": 0.0,
+      "loss": 46.2426,
+      "step": 50
+    },
+    {
+      "epoch": 0.020758731641496705,
+      "eval_loss": 0.5452532172203064,
+      "eval_runtime": 625.0682,
+      "eval_samples_per_second": 25.96,
+      "eval_steps_per_second": 3.246,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null