Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d4c9815dcef0b704f861e7e8ecfcc55b860421a2436541a5e4b0b90dcc1bd5
+oid sha256:c08037188ef677c586cb32bb7807d94e34d0dc404e891519dedfd72c61e6b543
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a209d4dbe079d2805dc48f82d8c7ff090c47dc34ae0ad57f827bcfe91314c80
+oid sha256:d644278f218be3ed5c32143681b1979ca36ec63726609e9da674a5ee188c50b7
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb7191e0c07dc950f8048f4702149372de41964dd8f8803818b51fd73af10e44
+oid sha256:c9d8173f58db73ea70c325cf0924b8eb79a2a51c58c15bd5634473408fec4604
 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": 2.5152595043182373,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.02789400278940028,
+  "best_metric": 2.433013916015625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.05578800557880056,
   "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": 18.406,
       "eval_steps_per_second": 4.632,
       "step": 10
+    },
+    {
+      "epoch": 0.03347280334728033,
+      "grad_norm": 0.858866810798645,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.4774,
+      "step": 12
+    },
+    {
+      "epoch": 0.04184100418410042,
+      "grad_norm": 0.6612495183944702,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.5047,
+      "step": 15
+    },
+    {
+      "epoch": 0.04184100418410042,
+      "eval_loss": 2.4529712200164795,
+      "eval_runtime": 16.4489,
+      "eval_samples_per_second": 18.36,
+      "eval_steps_per_second": 4.62,
+      "step": 15
+    },
+    {
+      "epoch": 0.0502092050209205,
+      "grad_norm": 0.446765273809433,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.3788,
+      "step": 18
+    },
+    {
+      "epoch": 0.05578800557880056,
+      "eval_loss": 2.433013916015625,
+      "eval_runtime": 16.4157,
+      "eval_samples_per_second": 18.397,
+      "eval_steps_per_second": 4.63,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7419001684623360.0,
+  "total_flos": 1.483800336924672e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null