Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:413b354da02ea4a4c315b76a60450c251be95a704fd5a691ce405f984587ea42
+oid sha256:38cf426c06810618dad0f9354819bb9e06933be9acd519a6fd895205f2839b2a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d8da4799f1cd62443c2768faa8dd6575543df4eb366327ab95c262d58bc06d
+oid sha256:175a8398a6baea8e2551a8e486e53a1a58494305cc35ce2c16116a0fd33bb275
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b10c3e127a6c4ecce16de496db8733195ccd36983fe9730fac5b2125e01dc1d0
+oid sha256:a0fe8548f93d4d2ba2061a5ff853229d8c4fc7065f047b09d11c7fb046ff6964
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4261242747306824,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0006386613657773307,
+  "best_metric": 0.2597002685070038,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0012773227315546615,
   "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": 6.237,
       "eval_steps_per_second": 3.119,
       "step": 10
+    },
+    {
+      "epoch": 0.0007025275023550638,
+      "grad_norm": 0.8175431489944458,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.4296,
+      "step": 11
+    },
+    {
+      "epoch": 0.0007663936389327968,
+      "grad_norm": 0.7449086904525757,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.4055,
+      "step": 12
+    },
+    {
+      "epoch": 0.0008302597755105299,
+      "grad_norm": 1.2498811483383179,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.3413,
+      "step": 13
+    },
+    {
+      "epoch": 0.000894125912088263,
+      "grad_norm": 0.8443876504898071,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.3248,
+      "step": 14
+    },
+    {
+      "epoch": 0.0009579920486659961,
+      "grad_norm": 0.8828296065330505,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.3644,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009579920486659961,
+      "eval_loss": 0.3001621663570404,
+      "eval_runtime": 1043.9309,
+      "eval_samples_per_second": 6.316,
+      "eval_steps_per_second": 3.158,
+      "step": 15
+    },
+    {
+      "epoch": 0.001021858185243729,
+      "grad_norm": 0.7488011717796326,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2425,
+      "step": 16
+    },
+    {
+      "epoch": 0.0010857243218214622,
+      "grad_norm": 0.6179611086845398,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.3411,
+      "step": 17
+    },
+    {
+      "epoch": 0.0011495904583991954,
+      "grad_norm": 0.7472450137138367,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.3922,
+      "step": 18
+    },
+    {
+      "epoch": 0.0012134565949769283,
+      "grad_norm": 0.6675222516059875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4745,
+      "step": 19
+    },
+    {
+      "epoch": 0.0012773227315546615,
+      "grad_norm": 0.5154255032539368,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.2231,
+      "step": 20
+    },
+    {
+      "epoch": 0.0012773227315546615,
+      "eval_loss": 0.2597002685070038,
+      "eval_runtime": 1046.8452,
+      "eval_samples_per_second": 6.298,
+      "eval_steps_per_second": 3.149,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2173237991571456.0,
+  "total_flos": 4485193301753856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null