Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f603b2d7bf80a84d4d78141b09ea081891bbb62d859374706bc958ba32fbed
+oid sha256:fc5a25d2b03537455c72adc1f9e2ca43035407fa9dc76e8a9dc7a1bbeed98d3e
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc696b3d9f426b5c1a0fa908306138958840ca2288ca35ecee2f9361c6e02b6
+oid sha256:43467a22bed0037c91247660e556e843b914d5f1ed50942668707b8205e07fbc
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5973a01737a9f64456c5ff2b95b8b9115f3aaa462dbf950c052bf4b3e478efd
+oid sha256:4a3ddff7b106093981ec215768911a1860737288ff6cc8633edcc8be32931504
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.963434934616089,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006763611768684477,
+  "best_metric": 3.928459882736206,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.010145417653026716,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 3.1,
       "eval_steps_per_second": 0.776,
       "step": 20
+    },
+    {
+      "epoch": 0.007101792357118702,
+      "grad_norm": 0.8026948571205139,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.7612,
+      "step": 21
+    },
+    {
+      "epoch": 0.008116334122421373,
+      "grad_norm": 1.0372897386550903,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.9055,
+      "step": 24
+    },
+    {
+      "epoch": 0.008454514710855596,
+      "eval_loss": 3.9400546550750732,
+      "eval_runtime": 804.2628,
+      "eval_samples_per_second": 3.096,
+      "eval_steps_per_second": 0.775,
+      "step": 25
+    },
+    {
+      "epoch": 0.009130875887724045,
+      "grad_norm": 0.9315910935401917,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.8441,
+      "step": 27
+    },
+    {
+      "epoch": 0.010145417653026716,
+      "grad_norm": 0.9024998545646667,
+      "learning_rate": 0.0,
+      "loss": 4.0826,
+      "step": 30
+    },
+    {
+      "epoch": 0.010145417653026716,
+      "eval_loss": 3.928459882736206,
+      "eval_runtime": 805.0922,
+      "eval_samples_per_second": 3.093,
+      "eval_steps_per_second": 0.774,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.8022017496252416e+16,
+  "total_flos": 2.5690961111678976e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null