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:e2c5702947788223a0aaf9442294e6ece5f7e3f4830d32448d427a8c1a37cabb
+oid sha256:fdbbfcffda580398ffa0d3e78b0e22e8f16d0673b217b7214cce3b347880f4aa
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6666ad101905d4add27373de45a106245dfb37f4e9289f2b657168bd69997d8b
+oid sha256:60b2db440eba876521bdf9d2dcf647c0c2813ca366a7e9eff636c249b0ed2e50
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f775c1ccf3d22e28827fb97e42f46af086c555f27d776c68d4071ccefdb3a7
+oid sha256:5225e37d7d543a33e698142d3eeff29567a056e9f14e596173f4a3fbf89f1212
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.64383864402771,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.05847953216374269,
+  "best_metric": 3.360213041305542,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.11695906432748537,
   "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": 19.018,
       "eval_steps_per_second": 9.509,
       "step": 10
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 3.6851561069488525,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 3.5827,
+      "step": 12
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "grad_norm": 2.6502652168273926,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.328,
+      "step": 15
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "eval_loss": 3.435582160949707,
+      "eval_runtime": 3.7881,
+      "eval_samples_per_second": 19.007,
+      "eval_steps_per_second": 9.503,
+      "step": 15
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.3518097400665283,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.348,
+      "step": 18
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "eval_loss": 3.360213041305542,
+      "eval_runtime": 3.7903,
+      "eval_samples_per_second": 18.996,
+      "eval_steps_per_second": 9.498,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1005298290524160.0,
+  "total_flos": 2010596581048320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null