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:b2727f4ea39eb9c80c380d35a235cbea65e39987cb0114d3b69174fcf5535d54
+oid sha256:f1859c3f5b8e0168827eae47bdb5fe9554e278e39a5431c70f04042d0601bcbd
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d673d65f77a9a4c41d48f133509fd5342ec5a2bb76f3e4f1fa7e67635a73ddb5
+oid sha256:3ece48abc7c7da51e41c25270922d7fe3d3ab3c4c8109e6dffca241bdbd5c566
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bab01eab550a306c972ce5ad2af26a8523e15f75072c5c05ca6fc17de31a995
+oid sha256:bc51cd0565630bf06c9961a9235822ecc41236b4c60ef3532aea20d601cf23bf
 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": 4.026662349700928,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003361627027481301,
+  "best_metric": 3.981193780899048,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005042440541221951,
   "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": 16.08,
       "eval_steps_per_second": 8.043,
       "step": 20
+    },
+    {
+      "epoch": 0.003529708378855366,
+      "grad_norm": 0.7595122456550598,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.8472,
+      "step": 21
+    },
+    {
+      "epoch": 0.004033952432977561,
+      "grad_norm": 0.7659631371498108,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.6731,
+      "step": 24
+    },
+    {
+      "epoch": 0.004202033784351626,
+      "eval_loss": 3.988229751586914,
+      "eval_runtime": 155.3708,
+      "eval_samples_per_second": 16.123,
+      "eval_steps_per_second": 8.065,
+      "step": 25
+    },
+    {
+      "epoch": 0.004538196487099756,
+      "grad_norm": 0.722743034362793,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.8237,
+      "step": 27
+    },
+    {
+      "epoch": 0.005042440541221951,
+      "grad_norm": 0.7678110599517822,
+      "learning_rate": 0.0,
+      "loss": 3.9421,
+      "step": 30
+    },
+    {
+      "epoch": 0.005042440541221951,
+      "eval_loss": 3.981193780899048,
+      "eval_runtime": 155.0573,
+      "eval_samples_per_second": 16.155,
+      "eval_steps_per_second": 8.081,
+      "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": 1029368772034560.0,
+  "total_flos": 1544053158051840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null