Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8cfc361c7861144cfc1dad353c74fe7ee1c61816bf32b650a3b35a3ee2b67f
+oid sha256:7f0a92132b5abeabd49eac72628f48c00c1999ab5e41b8e1ff6449dec85073ac
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee4b82cb60419ffc9ccb6c460e2eced60db2b9d8e317de2a29e76f8d9abfbc16
+oid sha256:5c8526ceea7abd5173465e95ac37d172c021c98cffec5036a0c8d76c78dbd3a3
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7faa78946358457fbea873c81336795a4dcfd01791f256cec9960ac24dd930
+oid sha256:e697cf9cc36b0a13279730091b4c6c6515c529d84fc9e847eeae1ffe72fe4ddf
 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": 1.9405193328857422,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.029850746268656716,
+  "best_metric": 1.92122220993042,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.05970149253731343,
   "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": 13.9,
       "eval_steps_per_second": 6.999,
       "step": 10
+    },
+    {
+      "epoch": 0.03582089552238806,
+      "grad_norm": 0.30999255180358887,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.9542,
+      "step": 12
+    },
+    {
+      "epoch": 0.04477611940298507,
+      "grad_norm": 0.3122391998767853,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.9043,
+      "step": 15
+    },
+    {
+      "epoch": 0.04477611940298507,
+      "eval_loss": 1.9285753965377808,
+      "eval_runtime": 10.3158,
+      "eval_samples_per_second": 13.668,
+      "eval_steps_per_second": 6.883,
+      "step": 15
+    },
+    {
+      "epoch": 0.05373134328358209,
+      "grad_norm": 0.31301966309547424,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.0048,
+      "step": 18
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "eval_loss": 1.92122220993042,
+      "eval_runtime": 10.4497,
+      "eval_samples_per_second": 13.493,
+      "eval_steps_per_second": 6.794,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1029368772034560.0,
+  "total_flos": 2058737544069120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null