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:eb17279a575af092347aade562b366d406f4cc411a3a5b0e0cc0b7492406d36d
+oid sha256:a296213106b39423eb0ac1fe490129891fc3f1d7bdb00e45d0ac1e06d11ebc20
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466d4c22af2c4f797a59d6d47c08cf98b89be71f645de18faa1016169f9567a0
+oid sha256:484f9e05b53b9fe5704f87120690fd54cdfd358b3ba30ecefafafaa2847108bd
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d92c9b98c045a4da28935bdb2ba9318d4407239dd9eb565c67b7ed70582236f
+oid sha256:a3fc42d49e32e12c6f7f951e821ec52062e026214ebb0bbcd1194c3b74d7856b
 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": 0.8160228729248047,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.11933174224343675,
+  "best_metric": 0.8120850920677185,
+  "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": 3.368,
       "eval_steps_per_second": 1.694,
       "step": 50
+    },
+    {
+      "epoch": 0.12171837708830549,
+      "grad_norm": 0.5184401273727417,
+      "learning_rate": 0.00019656487088855592,
+      "loss": 1.107,
+      "step": 51
+    },
+    {
+      "epoch": 0.12410501193317422,
+      "grad_norm": 0.42614543437957764,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 0.6306,
+      "step": 52
+    },
+    {
+      "epoch": 0.12649164677804295,
+      "grad_norm": 0.2956556975841522,
+      "learning_rate": 0.0001962237387768529,
+      "loss": 0.7877,
+      "step": 53
+    },
+    {
+      "epoch": 0.1288782816229117,
+      "grad_norm": 0.5040286779403687,
+      "learning_rate": 0.00019604723610310194,
+      "loss": 0.7839,
+      "step": 54
+    },
+    {
+      "epoch": 0.13126491646778043,
+      "grad_norm": 0.4167059063911438,
+      "learning_rate": 0.00019586678530366606,
+      "loss": 0.86,
+      "step": 55
+    },
+    {
+      "epoch": 0.13126491646778043,
+      "eval_loss": 0.8153512477874756,
+      "eval_runtime": 52.5424,
+      "eval_samples_per_second": 3.369,
+      "eval_steps_per_second": 1.694,
+      "step": 55
+    },
+    {
+      "epoch": 0.13365155131264916,
+      "grad_norm": 0.5592871308326721,
+      "learning_rate": 0.00019568239379617088,
+      "loss": 0.7068,
+      "step": 56
+    },
+    {
+      "epoch": 0.1360381861575179,
+      "grad_norm": 0.5967664122581482,
+      "learning_rate": 0.00019549406916022905,
+      "loss": 0.9163,
+      "step": 57
+    },
+    {
+      "epoch": 0.13842482100238662,
+      "grad_norm": 0.4031658470630646,
+      "learning_rate": 0.00019530181913712872,
+      "loss": 0.7602,
+      "step": 58
+    },
+    {
+      "epoch": 0.14081145584725538,
+      "grad_norm": 0.6687312722206116,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.8132,
+      "step": 59
+    },
+    {
+      "epoch": 0.1431980906921241,
+      "grad_norm": 0.5811920166015625,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 0.7686,
+      "step": 60
+    },
+    {
+      "epoch": 0.1431980906921241,
+      "eval_loss": 0.8120850920677185,
+      "eval_runtime": 52.5863,
+      "eval_samples_per_second": 3.366,
+      "eval_steps_per_second": 1.692,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -473,7 +559,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.81874442223616e+16,
+  "total_flos": 3.382493306683392e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null