Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82624bb31acdc07bd8d5365cd51c32048469affe22289a2922b11a114df4d392
+oid sha256:cd5a5b218836ae9290cee53df02a704e0134cc53b060aebc6e247756e4378d90
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1acdea9f6264acfec536e404d70c44d90d13e9be9be12afb4ff6b4321705ef03
+oid sha256:799aff9848a9a701ee367493a1d6705a40b3cf1bfd551f12c95e05c4dbf476d7
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b68afb9bb7ee1d59d6ca3378a8fcdaab9d911ac6b25c2201ebc1813e43ad50d
+oid sha256:5853d415f407ae4bf64328017876e841c27a919af3f241df7d78f051a0403a95
 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": 2.014415979385376,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 1.9988279342651367,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02577873254564984,
   "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": 94.534,
       "eval_steps_per_second": 47.267,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 3.5724215507507324,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 7.9293,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 3.9034876823425293,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.3426,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 2.0014724731445312,
+      "eval_runtime": 5.3041,
+      "eval_samples_per_second": 92.382,
+      "eval_steps_per_second": 46.191,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 3.288078784942627,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 8.4004,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 4.017270565032959,
+      "learning_rate": 0.0,
+      "loss": 8.1183,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 1.9988279342651367,
+      "eval_runtime": 5.1597,
+      "eval_samples_per_second": 94.966,
+      "eval_steps_per_second": 47.483,
+      "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": 92689341087744.0,
+  "total_flos": 137956228595712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null