Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e853e27fc0442092179d9b83582896230553492608192ee997363c8ca924ed
+oid sha256:b9106cc629280a730337d9bad4cb19db4e121ae1ecd428481842a9c8b5933f46
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225ce6cc098ddaccc08ba0fd2f58c85405165c0c4cabb9f9ee2489142f3ee9d6
+oid sha256:375d91cc24cbbf2877704752c9cd674cc5639272b357325445037c07f9eec8a1
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c45d5fdd1b3ec6f7967dc61e7400f21280f264854c17b649fbdeba8d795d980
+oid sha256:480aa6ff5a6f083ad33b37891b54e68c4f952c516afd822788630a1ad576f482
 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": 1.3468906879425049,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.10526315789473684,
+  "best_metric": 1.318974494934082,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.15789473684210525,
   "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": 17.311,
       "eval_steps_per_second": 4.328,
       "step": 20
+    },
+    {
+      "epoch": 0.11052631578947368,
+      "grad_norm": 2.1808433532714844,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 5.5852,
+      "step": 21
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 2.32429575920105,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 5.2769,
+      "step": 24
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "eval_loss": 1.321532964706421,
+      "eval_runtime": 9.2743,
+      "eval_samples_per_second": 17.252,
+      "eval_steps_per_second": 4.313,
+      "step": 25
+    },
+    {
+      "epoch": 0.14210526315789473,
+      "grad_norm": 2.4233052730560303,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 5.3304,
+      "step": 27
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 2.362999677658081,
+      "learning_rate": 0.0,
+      "loss": 5.1204,
+      "step": 30
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "eval_loss": 1.318974494934082,
+      "eval_runtime": 9.2727,
+      "eval_samples_per_second": 17.255,
+      "eval_steps_per_second": 4.314,
+      "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": 2400948458618880.0,
+  "total_flos": 3601422687928320.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null