Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d799623a0d4fc4f7b084cf47a96ceeba1b03594f35bc02cc72c68fbe4b5f4aa
+oid sha256:25b741c219456f5c0897df1b410a563f503678034057bbe2e71f4c2f7f7520be
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd922c0c8f27128c518d657d432979ef621a05209132d0b7bd199eb158f50254
+oid sha256:884bee2a7dc2b9a524984b1d103b3abe783afd4089d59a1a6a569a4a4c8a2bd9
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58445241b28eb44d0198e93e80b92a9944566e4e8dea5c1a877d894ef260c925
+oid sha256:5c0cad57676d282037ca3ab77062b282474c1dffdefc39525ec854426ab32c79
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.366350173950195,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0015064211200241028,
+  "best_metric": 10.362568855285645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0030128422400482057,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 284.025,
       "eval_steps_per_second": 71.032,
       "step": 10
+    },
+    {
+      "epoch": 0.0018077053440289234,
+      "grad_norm": 0.07582756876945496,
+      "learning_rate": 0.000163742398974869,
+      "loss": 10.3683,
+      "step": 12
+    },
+    {
+      "epoch": 0.002259631680036154,
+      "grad_norm": 0.08869104087352753,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3667,
+      "step": 15
+    },
+    {
+      "epoch": 0.002259631680036154,
+      "eval_loss": 10.364151954650879,
+      "eval_runtime": 19.8651,
+      "eval_samples_per_second": 281.398,
+      "eval_steps_per_second": 70.375,
+      "step": 15
+    },
+    {
+      "epoch": 0.002711558016043385,
+      "grad_norm": 0.09177450835704803,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 10.3665,
+      "step": 18
+    },
+    {
+      "epoch": 0.0030128422400482057,
+      "eval_loss": 10.362568855285645,
+      "eval_runtime": 19.983,
+      "eval_samples_per_second": 279.738,
+      "eval_steps_per_second": 69.96,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 523024465920.0,
+  "total_flos": 1046048931840.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null