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:f10d84b313ef4eb07cad4bd2f6097846e91c30ff8f1852123f816170bea7ca35
+oid sha256:362e2a98fe0857e2a72e2ae7f30f159a07659a0e80a74d95c070f1fc10ca19ae
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be54ae2baad83a59ed8be98cad9f43dd501367ee40b73975892c9e7919949b58
+oid sha256:e8139771901c4ef4dcef238de1d46301c6a8a3c3aaceadd8647988b3f89622ab
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33466b23035335e08a1321a4d680242421861125cde5f6829f13366cc17483de
+oid sha256:3a80a3e579a3578339ad82c7db2683bb137027e6bff46ee48b2584907b433862
 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": 2.3080296516418457,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004545971133083305,
+  "best_metric": 1.3011465072631836,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00909194226616661,
   "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": 76.876,
       "eval_steps_per_second": 38.479,
       "step": 10
+    },
+    {
+      "epoch": 0.005455165359699966,
+      "grad_norm": 39.956539154052734,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 8.7746,
+      "step": 12
+    },
+    {
+      "epoch": 0.006818956699624957,
+      "grad_norm": 54.049015045166016,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 7.4937,
+      "step": 15
+    },
+    {
+      "epoch": 0.006818956699624957,
+      "eval_loss": 1.537344217300415,
+      "eval_runtime": 12.1276,
+      "eval_samples_per_second": 76.437,
+      "eval_steps_per_second": 38.26,
+      "step": 15
+    },
+    {
+      "epoch": 0.008182748039549948,
+      "grad_norm": 91.98859405517578,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.0859,
+      "step": 18
+    },
+    {
+      "epoch": 0.00909194226616661,
+      "eval_loss": 1.3011465072631836,
+      "eval_runtime": 12.0011,
+      "eval_samples_per_second": 77.243,
+      "eval_steps_per_second": 38.663,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 177003319787520.0,
+  "total_flos": 354006639575040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null