Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9000a0dd97e5d6c2287fe480d724c947b4c5932f7d820c7c7e4629fc7b8bc0b0
+oid sha256:b03a816802d6280d08e02e3cb54744e7970dc77e7a365e2f3207c9b94ab963e1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beedf2babdb7cc6082ee9b418dca4bc86d53073ea26a85f35710fdebe00b6880
+oid sha256:817a9e0489b7439f11f0c377abb749e8b52b241ce816cdf45af5410d4987ca0f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bfa391c991296fbfb6ff3e05d93562c2acfb77e3fa8d5110805f323726fd70a
+oid sha256:8d2012a6de7a999ea78b56097d7e9d2e235c1748dbc12735f44ee82c3cec17f4
 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": 2.0532379150390625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.002073613271124935,
+  "best_metric": 1.7496976852416992,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00414722654224987,
   "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": 8.111,
       "eval_steps_per_second": 2.029,
       "step": 10
+    },
+    {
+      "epoch": 0.002488335925349922,
+      "grad_norm": 1.0966166257858276,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.887,
+      "step": 12
+    },
+    {
+      "epoch": 0.003110419906687403,
+      "grad_norm": 1.2030495405197144,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.8168,
+      "step": 15
+    },
+    {
+      "epoch": 0.003110419906687403,
+      "eval_loss": 1.81242835521698,
+      "eval_runtime": 500.6911,
+      "eval_samples_per_second": 8.111,
+      "eval_steps_per_second": 2.029,
+      "step": 15
+    },
+    {
+      "epoch": 0.0037325038880248835,
+      "grad_norm": 1.3473399877548218,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.844,
+      "step": 18
+    },
+    {
+      "epoch": 0.00414722654224987,
+      "eval_loss": 1.7496976852416992,
+      "eval_runtime": 500.9634,
+      "eval_samples_per_second": 8.106,
+      "eval_steps_per_second": 2.028,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.483774567120896e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null