Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80cf098083e6be16bf73641af06eb2fb48342ed707d928ce21893cc24ec9dfff
+oid sha256:f389911304f92ab58eb698f66b3ac0e48d070c621bce745dc17d147f54e7537d
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404883f9b49a9fbf8d42ca08d6de274fd3b30c021dc14e69f766dc8852dddf40
-size 71077780
+oid sha256:ab0fd06ca1ca12649f8df0c1ed1dc7b3c2caed3f8a0383ddd09112ac1313ccbb
+size 71078228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f60bbff6e8aecbb6064459455b86407666ac7ff107875eaadd58531a093350
+oid sha256:3f50080820ee4bc1eb5d6a8840fe09e2abe398388b748d57f3eefc4deca72b7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5245962b37abe5debb29d3c0771306ab720257c32ca897672f6c78751ec6642f
+oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7828339338302612,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.007337618502538816,
+  "best_metric": 1.7800281047821045,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.00880514220304658,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 67.868,
       "eval_steps_per_second": 16.969,
       "step": 250
+    },
+    {
+      "epoch": 0.007631123242640369,
+      "grad_norm": 0.4686952829360962,
+      "learning_rate": 0.00012039360249617425,
+      "loss": 1.904,
+      "step": 260
+    },
+    {
+      "epoch": 0.007924627982741921,
+      "grad_norm": 0.48834189772605896,
+      "learning_rate": 0.00011280404514057264,
+      "loss": 1.8579,
+      "step": 270
+    },
+    {
+      "epoch": 0.008218132722843474,
+      "grad_norm": 0.6082870364189148,
+      "learning_rate": 0.00010519595485942743,
+      "loss": 1.8033,
+      "step": 280
+    },
+    {
+      "epoch": 0.008511637462945027,
+      "grad_norm": 0.6713098883628845,
+      "learning_rate": 9.76063975038258e-05,
+      "loss": 1.761,
+      "step": 290
+    },
+    {
+      "epoch": 0.00880514220304658,
+      "grad_norm": 0.6551229953765869,
+      "learning_rate": 9.00723486343046e-05,
+      "loss": 1.5213,
+      "step": 300
+    },
+    {
+      "epoch": 0.00880514220304658,
+      "eval_loss": 1.7800281047821045,
+      "eval_runtime": 211.4964,
+      "eval_samples_per_second": 67.831,
+      "eval_steps_per_second": 16.96,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4009708431605760.0,
+  "total_flos": 4812508727869440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null