Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:506aacf045156cd8deca86f5c486d4e0f933510b8d7307a2dfbc61113829b507
+oid sha256:588ca0c83e24735f73595ee82f497df45bec56ce832ced394c7c4770938e245e
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9805fac5087be8e692af61b5f84fd7cc9c0957dfee82918a456701f187ad78
+oid sha256:3c61019809fca5673ba8052818cb0abcdb3db3eec75b7ad3810d1a4704ee642b
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
+oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.8797872066497803,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0001781039058186546,
+  "best_metric": 2.372363805770874,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0003562078116373092,
   "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": 9.058,
       "eval_steps_per_second": 4.53,
       "step": 10
+    },
+    {
+      "epoch": 0.00021372468698238552,
+      "grad_norm": 5.294992923736572,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.8922,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002671558587279819,
+      "grad_norm": 7.777354717254639,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.4119,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002671558587279819,
+      "eval_loss": 2.4778892993927,
+      "eval_runtime": 659.4412,
+      "eval_samples_per_second": 8.964,
+      "eval_steps_per_second": 4.483,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003205870304735783,
+      "grad_norm": 5.830846309661865,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.501,
+      "step": 18
+    },
+    {
+      "epoch": 0.0003562078116373092,
+      "eval_loss": 2.372363805770874,
+      "eval_runtime": 648.4012,
+      "eval_samples_per_second": 9.116,
+      "eval_steps_per_second": 4.559,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45059643801600.0,
+  "total_flos": 90119287603200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null