Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73a741af750adb7d1415da7efedfe348f3b047bb1d2355a0472bbf474ecdc402
+oid sha256:8935bfafa789138a481c5bad71bb5a7ea10a706ecff34beebf114a2ab4f7983a
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ffc44ed514d6d06cf6582a69b76587c0f29ff4eeb21f54ebe6e55e5c7c3aa49
+oid sha256:09c508cde67c3925c7371cfb386e458d46702c3d2dcd241ad994ae0c92127941
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d23c840bd94ef6552bc01b6a28ad0251374767cebf3f41d0bac1d52178aef7
+oid sha256:6cede45cbbdce36468e8158eea8799cc9dff789b8bd193b68d5b552ab2ee299b
 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": 1.330280065536499,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004802497298595269,
+  "best_metric": 1.313137412071228,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.007203745947892904,
   "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": 6.382,
       "eval_steps_per_second": 1.596,
       "step": 20
+    },
+    {
+      "epoch": 0.005042622163525033,
+      "grad_norm": 1.8446440696716309,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 5.3328,
+      "step": 21
+    },
+    {
+      "epoch": 0.005762996758314323,
+      "grad_norm": 1.8176443576812744,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 5.3829,
+      "step": 24
+    },
+    {
+      "epoch": 0.006003121623244087,
+      "eval_loss": 1.3164762258529663,
+      "eval_runtime": 549.4789,
+      "eval_samples_per_second": 6.382,
+      "eval_steps_per_second": 1.596,
+      "step": 25
+    },
+    {
+      "epoch": 0.006483371353103614,
+      "grad_norm": 1.9143404960632324,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 5.1801,
+      "step": 27
+    },
+    {
+      "epoch": 0.007203745947892904,
+      "grad_norm": 1.946859359741211,
+      "learning_rate": 0.0,
+      "loss": 5.1419,
+      "step": 30
+    },
+    {
+      "epoch": 0.007203745947892904,
+      "eval_loss": 1.313137412071228,
+      "eval_runtime": 549.3696,
+      "eval_samples_per_second": 6.384,
+      "eval_steps_per_second": 1.596,
+      "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": 2.28688285138944e+16,
+  "total_flos": 3.43032427708416e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null