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:d656e009930ae35250d72894a708c06dc2f37e57b705b038c8a50c0d85c74808
+oid sha256:5e6dd61b556050da5648a35d5e7d8f93275589f55704611f74356dbefa276cce
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be41250436dcbfc39c8409d471b7ca8cec33a786b310f647ec75e5e092b4baca
+oid sha256:408237144217d6bf1b0f11dcef515cc4b5f6fd04a345f52f7125d9e7f52880d1
 size 101107578

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f826c6530a855c1ffb12baefb1785cd55a6cd34509c056d1cb6a48e9253cc7a
+oid sha256:5d616c21e6738d673051c3b1bfe81804ed383456ad1f17d9fac066ae6f18c0ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6417946815490723,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008592910848549946,
+  "best_metric": 1.5292763710021973,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.017185821697099892,
   "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": 14.316,
       "eval_steps_per_second": 7.158,
       "step": 10
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 0.1880308836698532,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.6545,
+      "step": 12
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 0.1989935040473938,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.5914,
+      "step": 15
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "eval_loss": 1.5794165134429932,
+      "eval_runtime": 34.32,
+      "eval_samples_per_second": 14.277,
+      "eval_steps_per_second": 7.139,
+      "step": 15
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 0.15050296485424042,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5556,
+      "step": 18
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": 1.5292763710021973,
+      "eval_runtime": 34.2687,
+      "eval_samples_per_second": 14.299,
+      "eval_steps_per_second": 7.149,
+      "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