Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6378096fc7ddf0a67fc48acd7c102769f0865510615b50317155ddcd2889a8a2
+oid sha256:e65aee147809099eefaac04c987d5c58dad52ab10749cb19238f477690e94748
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b756ed530a3890a11fba9bedd29945d0b19331067d010cec38104f5c56480087
+oid sha256:4b8a72a17da46d7b083c69b65b18cf7f0f795935acd2f7c78481514fdd6d916b
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c943d058112e50245b1cdd5c0b0d33303a12582563405c5b98e52cbf596e61
+oid sha256:459b8ebc21da055bb58b68037491f81f6142db747d843dea15f6e43266294436
 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": 11.058859825134277,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0005617780274569011,
+  "best_metric": 11.051238059997559,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0008426670411853516,
   "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": 173.033,
       "eval_steps_per_second": 86.516,
       "step": 20
+    },
+    {
+      "epoch": 0.0005898669288297462,
+      "grad_norm": 1.1769465208053589,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 44.243,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006741336329482813,
+      "grad_norm": 1.2160230875015259,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 44.2339,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007022225343211264,
+      "eval_loss": 11.052404403686523,
+      "eval_runtime": 86.2812,
+      "eval_samples_per_second": 173.734,
+      "eval_steps_per_second": 86.867,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007584003370668165,
+      "grad_norm": 1.1281684637069702,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 44.1836,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008426670411853516,
+      "grad_norm": 1.247786045074463,
+      "learning_rate": 0.0,
+      "loss": 44.2118,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008426670411853516,
+      "eval_loss": 11.051238059997559,
+      "eval_runtime": 86.6222,
+      "eval_samples_per_second": 173.05,
+      "eval_steps_per_second": 86.525,
+      "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": 431590735872.0,
+  "total_flos": 655185936384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null