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:d4e49a950c72d42ec41f75e2a1c2a80a5277b6937ea0f01c799581f50163b517
+oid sha256:3048fb2a8e5e02968f0dd09e08a49591ed277ae2df33c4d16949e58878e32401
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705a3681ab3e6f8216c0e003e4681034bff968a15451223c14631cb0d9a55be0
+oid sha256:f6c290b31cf6ac3912a5c3d74029517f76c0f75e96865af9ac00a8c4594c7acd
 size 67216698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9711174c90f838f1f42238499e240f6a654db39abacf8df1650165bb63d26c
+oid sha256:7de9e73f6ae526c6d950b7fdc3b886b37d47bdb6b77018e2ff8b1e6809425a64
 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": 2.6887049674987793,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001992379149752198,
+  "best_metric": 2.674560308456421,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0029885687246282966,
   "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": 97.786,
       "eval_steps_per_second": 24.452,
       "step": 20
+    },
+    {
+      "epoch": 0.0020919981072398076,
+      "grad_norm": 3.3302981853485107,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.2059,
+      "step": 21
+    },
+    {
+      "epoch": 0.0023908549797026376,
+      "grad_norm": 3.383589029312134,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.6784,
+      "step": 24
+    },
+    {
+      "epoch": 0.0024904739371902473,
+      "eval_loss": 2.6769638061523438,
+      "eval_runtime": 86.3451,
+      "eval_samples_per_second": 97.909,
+      "eval_steps_per_second": 24.483,
+      "step": 25
+    },
+    {
+      "epoch": 0.002689711852165467,
+      "grad_norm": 3.4230642318725586,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 9.8712,
+      "step": 27
+    },
+    {
+      "epoch": 0.0029885687246282966,
+      "grad_norm": 3.292234420776367,
+      "learning_rate": 0.0,
+      "loss": 10.5659,
+      "step": 30
+    },
+    {
+      "epoch": 0.0029885687246282966,
+      "eval_loss": 2.674560308456421,
+      "eval_runtime": 86.2701,
+      "eval_samples_per_second": 97.995,
+      "eval_steps_per_second": 24.504,
+      "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": 1803185647779840.0,
+  "total_flos": 2704778471669760.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null