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:bde632ffcff2b7bfc8427f0cfc7367389ac5fe2df01f369cb13f8f928f8a5623
+oid sha256:3b1051c40f60c34d60602ae71228f1429c177143b6cf8ecac881815a937354e0
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86dd03c9eac661d4567700b1b6dd0c48cbad2f30f7f447cc92ddc046528091c3
+oid sha256:5d7004f62a2f55d8cd953a5f2bba0eff36b32f2227c1809e5cb658a5588a181e
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59dccbcd6e5d4694689dd3655d38cda4e38e65878a371ef0b6c906c0c871ff8e
+oid sha256:8309c0693e772fd4aebf77d82539ed89aacdaf3c8a388e005bbc99f6e21ab76e
 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": 0.9378935098648071,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.18691588785046728,
+  "best_metric": 0.9353803992271423,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.2803738317757009,
   "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": 26.758,
       "eval_steps_per_second": 6.838,
       "step": 20
+    },
+    {
+      "epoch": 0.19626168224299065,
+      "grad_norm": 0.9750715494155884,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.84,
+      "step": 21
+    },
+    {
+      "epoch": 0.22429906542056074,
+      "grad_norm": 1.1634858846664429,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.007,
+      "step": 24
+    },
+    {
+      "epoch": 0.2336448598130841,
+      "eval_loss": 0.9214831590652466,
+      "eval_runtime": 3.3654,
+      "eval_samples_per_second": 26.743,
+      "eval_steps_per_second": 6.834,
+      "step": 25
+    },
+    {
+      "epoch": 0.2523364485981308,
+      "grad_norm": 0.7800555229187012,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.2721,
+      "step": 27
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "grad_norm": 0.6685587167739868,
+      "learning_rate": 0.0,
+      "loss": 0.7286,
+      "step": 30
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "eval_loss": 0.9353803992271423,
+      "eval_runtime": 3.3644,
+      "eval_samples_per_second": 26.751,
+      "eval_steps_per_second": 6.836,
+      "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": 4071458076622848.0,
+  "total_flos": 6232849401249792.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null