Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a65e24ad21338879e1de739c936fe9ed072a93a8232a9e27737fac9b0d201b0
+oid sha256:ef93711743dc3b588728213f422de07f8bd02ecb119605ea8f9e390772960ef2
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc289aa2389b3c5dac8d19224615b1c45f4c3cbd1ffa0c436bbd49ba5347a6c
+oid sha256:b5b6bc9d711c4025b1f455dbd4238cbe54265fc2e3703b36f301876c51691198
 size 259758

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b25ea8f53b0678d8d1bb14f5e8854c8220a8a4816ce0f527cb7bd1f43724c1
+oid sha256:985a80c8c41363982edea6d90f4e902b8cfdba508f6bff3ca2a895fc4d429fd2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8bc8abd4c9f82dfc46828b9bd127304694d7b33110834b4b23e29a7f6b47fd
+oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.117691040039062,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0012305420537746877,
+  "best_metric": 11.116108894348145,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0024610841075493753,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 105.199,
       "eval_steps_per_second": 52.599,
       "step": 10
+    },
+    {
+      "epoch": 0.0013535962591521564,
+      "grad_norm": 0.8100368976593018,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 44.411,
+      "step": 11
+    },
+    {
+      "epoch": 0.0014766504645296252,
+      "grad_norm": 0.6994816660881042,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 44.4929,
+      "step": 12
+    },
+    {
+      "epoch": 0.0015997046699070942,
+      "grad_norm": 0.7958971858024597,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 44.4624,
+      "step": 13
+    },
+    {
+      "epoch": 0.001722758875284563,
+      "grad_norm": 0.733568549156189,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 44.468,
+      "step": 14
+    },
+    {
+      "epoch": 0.0018458130806620317,
+      "grad_norm": 0.7478417754173279,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 44.4557,
+      "step": 15
+    },
+    {
+      "epoch": 0.0018458130806620317,
+      "eval_loss": 11.1167631149292,
+      "eval_runtime": 32.8806,
+      "eval_samples_per_second": 104.073,
+      "eval_steps_per_second": 52.037,
+      "step": 15
+    },
+    {
+      "epoch": 0.0019688672860395003,
+      "grad_norm": 0.8152060508728027,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 44.4493,
+      "step": 16
+    },
+    {
+      "epoch": 0.0020919214914169692,
+      "grad_norm": 0.752731204032898,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 44.4793,
+      "step": 17
+    },
+    {
+      "epoch": 0.002214975696794438,
+      "grad_norm": 0.8056250810623169,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 44.4443,
+      "step": 18
+    },
+    {
+      "epoch": 0.0023380299021719068,
+      "grad_norm": 0.9155802130699158,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 44.3931,
+      "step": 19
+    },
+    {
+      "epoch": 0.0024610841075493753,
+      "grad_norm": 0.8312753438949585,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 44.4666,
+      "step": 20
+    },
+    {
+      "epoch": 0.0024610841075493753,
+      "eval_loss": 11.116108894348145,
+      "eval_runtime": 32.7053,
+      "eval_samples_per_second": 104.632,
+      "eval_steps_per_second": 52.316,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 130204827648.0,
+  "total_flos": 262820855808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null