Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a0ce744c574dde5ff01d54cbde9aaf4826321e6dbab34fba0301d723d5f12af
+oid sha256:90bf8b1abd077560ae21524bb4b9db9586219a179e281917a253696ddb8257bc
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74aa14ddf23ce2fdd4b7f8ae4bf9b779c8c56b388e745f1fc77cb88b58b464a
+oid sha256:262a50e5a7cc8f345a277592b0f488331df7618f612800c3a2617d850e787308
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d70924c232436c800df90f52f87adf6e3125c020b3b0e481f02d258de1cd8e9
+oid sha256:44059b09209f87972294b03cfee10b90679da0d01bc9e481ff780b446fb3e5e2
 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": 11.067892074584961,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.002259835935911053,
+  "best_metric": 11.05736255645752,
+  "best_model_checkpoint": "miner_id_24/checkpoint-60",
+  "epoch": 0.0027118031230932635,
   "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": 52.78,
       "eval_steps_per_second": 26.393,
       "step": 50
+    },
+    {
+      "epoch": 0.002305032654629274,
+      "grad_norm": 0.7787512540817261,
+      "learning_rate": 0.00019656487088855592,
+      "loss": 44.2918,
+      "step": 51
+    },
+    {
+      "epoch": 0.002350229373347495,
+      "grad_norm": 0.7184544801712036,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 44.2751,
+      "step": 52
+    },
+    {
+      "epoch": 0.002395426092065716,
+      "grad_norm": 0.7348573803901672,
+      "learning_rate": 0.0001962237387768529,
+      "loss": 44.246,
+      "step": 53
+    },
+    {
+      "epoch": 0.002440622810783937,
+      "grad_norm": 0.7713965773582458,
+      "learning_rate": 0.00019604723610310194,
+      "loss": 44.3292,
+      "step": 54
+    },
+    {
+      "epoch": 0.002485819529502158,
+      "grad_norm": 0.8040369749069214,
+      "learning_rate": 0.00019586678530366606,
+      "loss": 44.2155,
+      "step": 55
+    },
+    {
+      "epoch": 0.002485819529502158,
+      "eval_loss": 11.062650680541992,
+      "eval_runtime": 176.278,
+      "eval_samples_per_second": 52.854,
+      "eval_steps_per_second": 26.43,
+      "step": 55
+    },
+    {
+      "epoch": 0.0025310162482203792,
+      "grad_norm": 0.7459877133369446,
+      "learning_rate": 0.00019568239379617088,
+      "loss": 44.2188,
+      "step": 56
+    },
+    {
+      "epoch": 0.0025762129669386004,
+      "grad_norm": 0.8008533716201782,
+      "learning_rate": 0.00019549406916022905,
+      "loss": 44.226,
+      "step": 57
+    },
+    {
+      "epoch": 0.002621409685656821,
+      "grad_norm": 0.7918010354042053,
+      "learning_rate": 0.00019530181913712872,
+      "loss": 44.287,
+      "step": 58
+    },
+    {
+      "epoch": 0.0026666064043750423,
+      "grad_norm": 0.7287217974662781,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 44.2581,
+      "step": 59
+    },
+    {
+      "epoch": 0.0027118031230932635,
+      "grad_norm": 0.7925474643707275,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 44.2277,
+      "step": 60
+    },
+    {
+      "epoch": 0.0027118031230932635,
+      "eval_loss": 11.05736255645752,
+      "eval_runtime": 176.2465,
+      "eval_samples_per_second": 52.863,
+      "eval_steps_per_second": 26.435,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -473,7 +559,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 525336576000.0,
+  "total_flos": 630403891200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null