Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976da714f3f898f1f10bfbb4ba95df598b7dcebd1e5b78060769e4f462fe113f
+oid sha256:f397b6efc99a54b6e2053a923d619243a9ae4cba4a980fedb47ede8680ad5710
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b659afda49dbfd370ec2b028222e8a409f393cc3fe2c8221301daa94e2c550e
+oid sha256:a1bce5e719182adcb4789dd3d1171ecc789c0877ed86cfbcb8050fdf09f47615
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc1e9d97c15596a1871118a958d12bbd6e6841c49442487b5a1cb68d58c088d
+oid sha256:d5c45a9d7925934b5907674a393a06a441b92cdf4c94dcc2de8c5597b2978120
 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": 2.0186400413513184,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.014270424545130217,
+  "best_metric": 1.9905468225479126,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.028540849090260435,
   "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": 8.925,
       "eval_steps_per_second": 2.239,
       "step": 10
+    },
+    {
+      "epoch": 0.01712450945415626,
+      "grad_norm": 0.8391133546829224,
+      "learning_rate": 0.000163742398974869,
+      "loss": 8.3792,
+      "step": 12
+    },
+    {
+      "epoch": 0.021405636817695327,
+      "grad_norm": 0.5525553226470947,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.1928,
+      "step": 15
+    },
+    {
+      "epoch": 0.021405636817695327,
+      "eval_loss": 1.9936939477920532,
+      "eval_runtime": 66.5146,
+      "eval_samples_per_second": 8.87,
+      "eval_steps_per_second": 2.225,
+      "step": 15
+    },
+    {
+      "epoch": 0.025686764181234393,
+      "grad_norm": 0.9312046766281128,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 8.188,
+      "step": 18
+    },
+    {
+      "epoch": 0.028540849090260435,
+      "eval_loss": 1.9905468225479126,
+      "eval_runtime": 66.4999,
+      "eval_samples_per_second": 8.872,
+      "eval_steps_per_second": 2.226,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.306929288708096e+16,
+  "total_flos": 2.613858577416192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null