Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc0e68d04a8adfe05f020eec034e0e59d91a71f07c79c3a0a7f9a8584e71807
+oid sha256:f6be9579da50ba672bf419110b7984009ef690591f0f5b3304a32b9cad9ee73e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2102b2582e5f00213097a440c3db44509f663309f67c2a4ce09b38a0c343d6e3
+oid sha256:26e28cc20cf83894135f0b32e65ec37e9b81a1ad0bd92f3250cc3e8644c73995
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b8d89a40030b9a750b4a9e65337810998732fa3148ed66231305958cc1accf
+oid sha256:cb562d6607a07d2765a7deac2718bf8d421b3b569e9dc9d32b110adc58a52a31
 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": 1.7495075464248657,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00414722654224987,
+  "best_metric": 1.7267781496047974,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.006220839813374806,
   "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": 18.513,
       "eval_steps_per_second": 4.632,
       "step": 20
+    },
+    {
+      "epoch": 0.004354587869362364,
+      "grad_norm": 1.3541162014007568,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.5605,
+      "step": 21
+    },
+    {
+      "epoch": 0.004976671850699844,
+      "grad_norm": 1.2817682027816772,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.6282,
+      "step": 24
+    },
+    {
+      "epoch": 0.005184033177812338,
+      "eval_loss": 1.7315082550048828,
+      "eval_runtime": 219.5222,
+      "eval_samples_per_second": 18.499,
+      "eval_steps_per_second": 4.628,
+      "step": 25
+    },
+    {
+      "epoch": 0.005598755832037325,
+      "grad_norm": 1.4769186973571777,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.6777,
+      "step": 27
+    },
+    {
+      "epoch": 0.006220839813374806,
+      "grad_norm": 1.5718729496002197,
+      "learning_rate": 0.0,
+      "loss": 1.6583,
+      "step": 30
+    },
+    {
+      "epoch": 0.006220839813374806,
+      "eval_loss": 1.7267781496047974,
+      "eval_runtime": 219.7223,
+      "eval_samples_per_second": 18.482,
+      "eval_steps_per_second": 4.624,
+      "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": 1.483774567120896e+16,
+  "total_flos": 2.225661850681344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null