Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a325469530c5116393c590cef5706d3eee407287829ff8aba0243257c6a3e152
+oid sha256:62f05558c21d49cb9e7b7542371d3bd7e5fa7c4e23a524cb4a2e2d951ce767b7
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a1ea3e95e617f44c829178caeeb753eb9447db9a8173560f8f0ca712a74448
+oid sha256:b111a7ec6a458128370132327494eb113dae7f9904096d27da271d0689cf8b08
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478569fdd6c2c85cc9a9d4f3f42aedfcff08e9b9c0032e129370e035f8798baf
+oid sha256:35155c640e8cacf8f819b6b10fb25c906257dbef0b22d3a1ba399ce4e53aa194
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc2bf0eccc6c4e85c949c664a83bcd160767da77920eebf352a6f7f7c4c9b2e
+oid sha256:54b996514a941dd419a3f7869454171b960cb51cf1b91d9b10dbdcf1b1e50a10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8324581384658813,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.11933174224343675,
+  "best_metric": 0.8281893730163574,
+  "best_model_checkpoint": "miner_id_24/checkpoint-60",
+  "epoch": 0.1431980906921241,
   "eval_steps": 5,
-  "global_step": 50,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -445,6 +445,92 @@
       "eval_samples_per_second": 6.724,
       "eval_steps_per_second": 3.381,
       "step": 50
+    },
+    {
+      "epoch": 0.12171837708830549,
+      "grad_norm": 0.35318946838378906,
+      "learning_rate": 0.00019656487088855592,
+      "loss": 1.033,
+      "step": 51
+    },
+    {
+      "epoch": 0.12410501193317422,
+      "grad_norm": 0.30267930030822754,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 0.6305,
+      "step": 52
+    },
+    {
+      "epoch": 0.12649164677804295,
+      "grad_norm": 0.30554893612861633,
+      "learning_rate": 0.0001962237387768529,
+      "loss": 0.7148,
+      "step": 53
+    },
+    {
+      "epoch": 0.1288782816229117,
+      "grad_norm": 0.3179020583629608,
+      "learning_rate": 0.00019604723610310194,
+      "loss": 0.6932,
+      "step": 54
+    },
+    {
+      "epoch": 0.13126491646778043,
+      "grad_norm": 0.43141505122184753,
+      "learning_rate": 0.00019586678530366606,
+      "loss": 0.9695,
+      "step": 55
+    },
+    {
+      "epoch": 0.13126491646778043,
+      "eval_loss": 0.8304810523986816,
+      "eval_runtime": 26.2933,
+      "eval_samples_per_second": 6.732,
+      "eval_steps_per_second": 3.385,
+      "step": 55
+    },
+    {
+      "epoch": 0.13365155131264916,
+      "grad_norm": 0.37711283564567566,
+      "learning_rate": 0.00019568239379617088,
+      "loss": 1.0899,
+      "step": 56
+    },
+    {
+      "epoch": 0.1360381861575179,
+      "grad_norm": 0.3021875023841858,
+      "learning_rate": 0.00019549406916022905,
+      "loss": 0.5727,
+      "step": 57
+    },
+    {
+      "epoch": 0.13842482100238662,
+      "grad_norm": 0.4609815180301666,
+      "learning_rate": 0.00019530181913712872,
+      "loss": 0.8931,
+      "step": 58
+    },
+    {
+      "epoch": 0.14081145584725538,
+      "grad_norm": 0.410404235124588,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.9462,
+      "step": 59
+    },
+    {
+      "epoch": 0.1431980906921241,
+      "grad_norm": 0.3426823318004608,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 0.767,
+      "step": 60
+    },
+    {
+      "epoch": 0.1431980906921241,
+      "eval_loss": 0.8281893730163574,
+      "eval_runtime": 26.309,
+      "eval_samples_per_second": 6.728,
+      "eval_steps_per_second": 3.383,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -473,7 +559,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9788035851878400.0,
+  "total_flos": 1.174564302225408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null