Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51917c99fb07ac99486ad7cc72833ed881fd742253dada44e741dd859af7a1fb
+oid sha256:11d4be2848dbc422d6adb8ecc783d7680e560b11846dbd4c1c6e88fd1fdd5d4f
 size 313820248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338c063679dd07d06313cc227bb8d0811eb1834cd4472d075ce09e4c7c83db96
+oid sha256:63286b2c7621ad84c65c085dc2912b773ccc240e8682a5b5f6807e1db62464e6
 size 159641092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b9779bcef08728811988d1ef1047135a6d1c22911b9db2bfe6e29b64418c0f
+oid sha256:667f71f48e843e3974cbf8fee3584d5e19776056dbcabf317190ff336db531b7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e231c2c515a5ff10f1e544b2aa46a8eaae94bd71a11db0123cabe0d1726bb1ba
+oid sha256:80e3c543dd881d7b92b58f753c91bcd488f8269b3e4ffd67623431c55e782209
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8345727920532227,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0032418588818828717,
+  "best_metric": 1.7966933250427246,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.004862788322824307,
   "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": 32.604,
       "eval_steps_per_second": 8.151,
       "step": 100
+    },
+    {
+      "epoch": 0.0035660447700711587,
+      "grad_norm": 3.908578872680664,
+      "learning_rate": 0.00019805195486600916,
+      "loss": 2.0062,
+      "step": 110
+    },
+    {
+      "epoch": 0.003890230658259446,
+      "grad_norm": 3.713029623031616,
+      "learning_rate": 0.00019488507586089894,
+      "loss": 1.7925,
+      "step": 120
+    },
+    {
+      "epoch": 0.004214416546447733,
+      "grad_norm": 4.107682704925537,
+      "learning_rate": 0.00019127297795219008,
+      "loss": 1.8635,
+      "step": 130
+    },
+    {
+      "epoch": 0.00453860243463602,
+      "grad_norm": 5.115502834320068,
+      "learning_rate": 0.00018723325891780706,
+      "loss": 1.8397,
+      "step": 140
+    },
+    {
+      "epoch": 0.004862788322824307,
+      "grad_norm": 4.171757221221924,
+      "learning_rate": 0.0001827855998628142,
+      "loss": 1.8328,
+      "step": 150
+    },
+    {
+      "epoch": 0.004862788322824307,
+      "eval_loss": 1.7966933250427246,
+      "eval_runtime": 397.1601,
+      "eval_samples_per_second": 32.702,
+      "eval_steps_per_second": 8.176,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5544499086360576.0,
+  "total_flos": 8354724650680320.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null