Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f84b04a2eeb38966d2568328a5f593d47120546b5da65834b39943e338bf5a
+oid sha256:fdd8dd8d069dd5c75a3e424b85f4d13382b6c86bc05cc911ebf92da15f8a1fe0
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eadbf4aa7bba76fbb78467943f0a75b696861b0d1e360998af6a6e98a501ea42
+oid sha256:5504ebdbd2f7e9cf940369b990abe257dfe79e6dd7545676351f27ccbf8ee600
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ed9ebb7297ee2e0f818b649d564c25c55944ce776d4f6fb15d80ba0ede6b9d
+oid sha256:7577594cb2e923f0986dcd66099d06bc38653ca89937b5665a0cf443b5a214d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f9eefb79e5a651e4979588997923d1fc997984394f03e9fb61aca38c6bee05
+oid sha256:e6da36b358afefa2fe6fe8e3889efc77dfb89ac577ed7bb55c631123a9ebe149
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.587920069694519,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0859106529209622,
+  "best_metric": 1.571736454963684,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.12886597938144329,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 20.349,
       "eval_steps_per_second": 5.108,
       "step": 100
+    },
+    {
+      "epoch": 0.09450171821305842,
+      "grad_norm": 0.6418641209602356,
+      "learning_rate": 5.05e-06,
+      "loss": 1.5007,
+      "step": 110
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 0.5860769748687744,
+      "learning_rate": 4.488888888888889e-06,
+      "loss": 1.5939,
+      "step": 120
+    },
+    {
+      "epoch": 0.11168384879725086,
+      "grad_norm": 0.5860627889633179,
+      "learning_rate": 3.927777777777778e-06,
+      "loss": 1.5596,
+      "step": 130
+    },
+    {
+      "epoch": 0.12027491408934708,
+      "grad_norm": 0.6728429198265076,
+      "learning_rate": 3.3666666666666665e-06,
+      "loss": 1.5375,
+      "step": 140
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 1.1351910829544067,
+      "learning_rate": 2.8055555555555555e-06,
+      "loss": 1.5916,
+      "step": 150
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "eval_loss": 1.571736454963684,
+      "eval_runtime": 24.0175,
+      "eval_samples_per_second": 20.402,
+      "eval_steps_per_second": 5.121,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9943329193984e+16,
+  "total_flos": 4.4914993790976e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null