Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f8ba1a7566d953e4f6bd8b51a55d60246f663a8fd2f0c6bb0d3b05ec2fc7e4
+oid sha256:c9288ef46aa5d544b76f9451237d30d9049b14079c1ac7f180d46546eb15469c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b0952a742e4621ae6007042d08b7f283dee4449f95a5a8fc212ccfc6ba71797
+oid sha256:f911fc8171094819af2cfa4214b6ab4af4b0692ed10d7cb316a0c612923a4764
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4769c32ac7a0b50b6a84655d674cc7d766891952a2a2a7f72f55a20a4c8f319d
+oid sha256:851c85ecac5e06dc623e477c5d362a544709dbbd36590caace940ad76524faff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.98299241065979,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008455765775288025,
+  "best_metric": 0.9622511267662048,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.012683648662932036,
   "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": 7.281,
       "eval_steps_per_second": 3.64,
       "step": 20
+    },
+    {
+      "epoch": 0.008878554064052425,
+      "grad_norm": 7.331959247589111,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.228,
+      "step": 21
+    },
+    {
+      "epoch": 0.01014691893034563,
+      "grad_norm": 5.93434476852417,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.9821,
+      "step": 24
+    },
+    {
+      "epoch": 0.01056970721911003,
+      "eval_loss": 0.9660122394561768,
+      "eval_runtime": 137.0324,
+      "eval_samples_per_second": 7.268,
+      "eval_steps_per_second": 3.634,
+      "step": 25
+    },
+    {
+      "epoch": 0.011415283796638833,
+      "grad_norm": 7.390657424926758,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.8016,
+      "step": 27
+    },
+    {
+      "epoch": 0.012683648662932036,
+      "grad_norm": 6.83233118057251,
+      "learning_rate": 0.0,
+      "loss": 3.8984,
+      "step": 30
+    },
+    {
+      "epoch": 0.012683648662932036,
+      "eval_loss": 0.9622511267662048,
+      "eval_runtime": 136.8086,
+      "eval_samples_per_second": 7.28,
+      "eval_steps_per_second": 3.64,
+      "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": 7646542055866368.0,
+  "total_flos": 1.1250084863803392e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null