Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722d1db81820628cc04c89066376d59950634b5aad2db0bf5a36dc80dc9c153d
+oid sha256:720afe2ffc93d8803c750ac3dfef466173b580025fb76a9d1ed1ca1f67a161eb
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89ef893f4ebc6c3d132eb9f54f3af0644f26ea92847b08697a7c71354d467a9e
+oid sha256:89796735b56af03f26c374c6be1806a5b10cdf4343eb3450c6b690817fd241fc
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239693e13e2f6d8495bdfafd2226d82b21048e203f3c56d74c68252d1c8be5fa
+oid sha256:3f7377b9ace87e5d1348a371868e70db5975a59da41f6f7f9ecea3bfa2375b75
 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": 1.5474625825881958,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0003989706557082727,
+  "best_metric": 1.4674350023269653,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0007979413114165454,
   "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": 7.535,
       "eval_steps_per_second": 3.767,
       "step": 10
+    },
+    {
+      "epoch": 0.0004787647868499272,
+      "grad_norm": 0.679478645324707,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.4392,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005984559835624089,
+      "grad_norm": 0.6193722486495972,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4252,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005984559835624089,
+      "eval_loss": 1.4833612442016602,
+      "eval_runtime": 1400.8261,
+      "eval_samples_per_second": 7.534,
+      "eval_steps_per_second": 3.767,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007181471802748908,
+      "grad_norm": 0.6720569729804993,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.4868,
+      "step": 18
+    },
+    {
+      "epoch": 0.0007979413114165454,
+      "eval_loss": 1.4674350023269653,
+      "eval_runtime": 1399.9143,
+      "eval_samples_per_second": 7.539,
+      "eval_steps_per_second": 3.77,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null