Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374f7d3f96c037724c7c5329e4eab3a809b4fdbbb9095b031b1a7c497a5e92f9
+oid sha256:6a53de4f2e6e0b8d189a3771a031977c04478ec8bd2e465405fabc0c6c9b1acc
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9497d4d04ddb7e9089cba9b807d767b815dd343704a171700e5ad9f79830ed9a
+oid sha256:c341ba9f85d67e0c1e72cee9b14de78096836870f12ef44e4c0feb7acec4e10f
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f9d4df5fa80b8af0ae9e036c834f318a3d9c628c3b781762ee3d1f9db0527c
+oid sha256:0fc2cf6684b4b4476cd2888efa54a33bf379ef1e654c5e672ef4c940dae96161
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
+oid sha256:7e45926e8bb4228c69b4b56f6b51f1445c0aeb3fb7bb09ed84764ec2b4c3a8ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.560912847518921,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0859106529209622,
+  "best_metric": 1.5504170656204224,
+  "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": 12.715,
       "eval_steps_per_second": 3.192,
       "step": 100
+    },
+    {
+      "epoch": 0.09450171821305842,
+      "grad_norm": 0.402596652507782,
+      "learning_rate": 3.1076923076923076e-06,
+      "loss": 1.4742,
+      "step": 110
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 0.44944673776626587,
+      "learning_rate": 2.330769230769231e-06,
+      "loss": 1.5515,
+      "step": 120
+    },
+    {
+      "epoch": 0.11168384879725086,
+      "grad_norm": 0.49855318665504456,
+      "learning_rate": 1.5538461538461538e-06,
+      "loss": 1.4891,
+      "step": 130
+    },
+    {
+      "epoch": 0.12027491408934708,
+      "grad_norm": 0.6558817625045776,
+      "learning_rate": 7.769230769230769e-07,
+      "loss": 1.55,
+      "step": 140
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 1.13808274269104,
+      "learning_rate": 0.0,
+      "loss": 1.6054,
+      "step": 150
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "eval_loss": 1.5504170656204224,
+      "eval_runtime": 38.7755,
+      "eval_samples_per_second": 12.637,
+      "eval_steps_per_second": 3.172,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -124,12 +167,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.9793401356288e+16,
+  "total_flos": 7.4690102034432e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null