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:b3ebae6745992a9891531c7f9dc21af61684fec4cad0bdb8ec71e2d7e0190098
+oid sha256:1349c39706954f73b87ce2e0d506e00758e8b213bb17e1a6dd1aed5c3f715b64
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086c8bf4279e90d468163e6119ad5a62eca1c60efa475a439bfc8e41ebe89eaa
+oid sha256:76e9ed812ac31db5016397a98d34a65c97abc515da8c38a3f1a9ed81553a05d4
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b715727f08f3bec1a4243110369e5be33fa530d65244e67bf09606e5d6da48
+oid sha256:78f4cc9cdab22e1e0f660a41fa1d4cd32f78600a13210572d12e13002a5dbf56
 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": 1.6434087753295898,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.014119308153900459,
+  "best_metric": 1.633779525756836,
+  "best_model_checkpoint": "miner_id_24/checkpoint-60",
+  "epoch": 0.01694316978468055,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,84 @@
       "eval_samples_per_second": 5.593,
       "eval_steps_per_second": 5.593,
       "step": 50
+    },
+    {
+      "epoch": 0.014401694316978467,
+      "grad_norm": 2.5457074642181396,
+      "learning_rate": 0.00019656487088855592,
+      "loss": 1.5371,
+      "step": 51
+    },
+    {
+      "epoch": 0.014684080480056478,
+      "grad_norm": 2.4005753993988037,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 1.0716,
+      "step": 52
+    },
+    {
+      "epoch": 0.014966466643134486,
+      "grad_norm": 2.4281392097473145,
+      "learning_rate": 0.0001962237387768529,
+      "loss": 2.1807,
+      "step": 53
+    },
+    {
+      "epoch": 0.015248852806212496,
+      "grad_norm": 2.5013136863708496,
+      "learning_rate": 0.00019604723610310194,
+      "loss": 1.0288,
+      "step": 54
+    },
+    {
+      "epoch": 0.015531238969290505,
+      "grad_norm": 2.0805702209472656,
+      "learning_rate": 0.00019586678530366606,
+      "loss": 1.1582,
+      "step": 55
+    },
+    {
+      "epoch": 0.015813625132368513,
+      "grad_norm": 7.539531707763672,
+      "learning_rate": 0.00019568239379617088,
+      "loss": 1.7791,
+      "step": 56
+    },
+    {
+      "epoch": 0.016096011295446522,
+      "grad_norm": 1.5069524049758911,
+      "learning_rate": 0.00019549406916022905,
+      "loss": 1.6449,
+      "step": 57
+    },
+    {
+      "epoch": 0.016378397458524534,
+      "grad_norm": 1.1627360582351685,
+      "learning_rate": 0.00019530181913712872,
+      "loss": 1.2881,
+      "step": 58
+    },
+    {
+      "epoch": 0.016660783621602542,
+      "grad_norm": 5.9471282958984375,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.6948,
+      "step": 59
+    },
+    {
+      "epoch": 0.01694316978468055,
+      "grad_norm": 1.4962432384490967,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 1.3254,
+      "step": 60
+    },
+    {
+      "epoch": 0.01694316978468055,
+      "eval_loss": 1.633779525756836,
+      "eval_runtime": 133.2937,
+      "eval_samples_per_second": 5.597,
+      "eval_steps_per_second": 5.597,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -433,7 +511,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4894017925939200.0,
+  "total_flos": 5872821511127040.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null