Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e682fb60bbe69332589d19a9d8a5fae0089210454c358fdfce12fc171baabb9
+oid sha256:d0fe091458a9c33e1b512530650c4da3bcd9060281e12b5e4622a213261dc0fe
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27532dae95400dd07acab5f183e710010d6cd9d16a3fd09ac525a79f55da2aac
+oid sha256:169efa28af1c92d9aa60f8a2aa2617ce6fa8a582b51df21067c6bf650dad0d9a
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a235bd5b22847df5efc576b2d53304138bedaafdab52b3f19ffc508dcd8204f7
+oid sha256:0a7ec423b1e2a3fc2ca790ddc4370fec88c8249a3964daf8a870d6f32dd37903
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a3e320c25c1cf347f88568a437fc2e5f443dd7786e10ada183f6eef07ff5147
+oid sha256:1645d5960cffb716058498f15a18dead45abc30cdbe88bcf0f6d3a17de954548
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4966574907302856,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.03678499172337686,
+  "best_metric": 1.4765535593032837,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.05517748758506529,
   "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": 17.355,
       "eval_steps_per_second": 4.35,
       "step": 100
+    },
+    {
+      "epoch": 0.04046349089571455,
+      "grad_norm": 0.8478430509567261,
+      "learning_rate": 0.0001932680912219027,
+      "loss": 1.5648,
+      "step": 110
+    },
+    {
+      "epoch": 0.044141990068052236,
+      "grad_norm": 0.9589736461639404,
+      "learning_rate": 0.00019017770687875164,
+      "loss": 1.4468,
+      "step": 120
+    },
+    {
+      "epoch": 0.047820489240389924,
+      "grad_norm": 0.9376389384269714,
+      "learning_rate": 0.000186652857711799,
+      "loss": 1.4539,
+      "step": 130
+    },
+    {
+      "epoch": 0.051498988412727605,
+      "grad_norm": 0.8931785821914673,
+      "learning_rate": 0.00018271071643186968,
+      "loss": 1.3959,
+      "step": 140
+    },
+    {
+      "epoch": 0.05517748758506529,
+      "grad_norm": 1.1111578941345215,
+      "learning_rate": 0.00017837048875501678,
+      "loss": 1.3041,
+      "step": 150
+    },
+    {
+      "epoch": 0.05517748758506529,
+      "eval_loss": 1.4765535593032837,
+      "eval_runtime": 66.144,
+      "eval_samples_per_second": 17.311,
+      "eval_steps_per_second": 4.339,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7773608566784e+16,
+  "total_flos": 2.6660412850176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null