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:badf45f5e865822f3e7e34c6f269a8158422260f1659f74f80dfa68e9f3e7634
+oid sha256:8718e1eba1a65bba613b3ca472e228f493db4f11afcaa7127a260af22e44ce44
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:921092be1eb49809262f7f2734ae9ff86a49cadb47f225ffda0b733f417ae9b8
+oid sha256:a1f90fdd8e6144050132a1a21b66d32e3b58440aead80d8056fc4b400989fe34
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bffebfc10014e1f2a28643f86c4ae249f581f79f287dd131cc1d5d4baf2eff
+oid sha256:63349ed6430faee6e096502bd3ba8e950be4cfef963239a5ceb870789f6de8d0
 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": 1.3166388273239136,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.022707919386886176,
+  "best_metric": 1.303216814994812,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.03406187908032927,
   "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": 25.175,
       "eval_steps_per_second": 12.621,
       "step": 20
+    },
+    {
+      "epoch": 0.023843315356230486,
+      "grad_norm": 0.42704302072525024,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.2463,
+      "step": 21
+    },
+    {
+      "epoch": 0.02724950326426341,
+      "grad_norm": 0.5720973014831543,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.2871,
+      "step": 24
+    },
+    {
+      "epoch": 0.02838489923360772,
+      "eval_loss": 1.3052393198013306,
+      "eval_runtime": 15.1912,
+      "eval_samples_per_second": 24.422,
+      "eval_steps_per_second": 12.244,
+      "step": 25
+    },
+    {
+      "epoch": 0.03065569117229634,
+      "grad_norm": 0.5630245804786682,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.2883,
+      "step": 27
+    },
+    {
+      "epoch": 0.03406187908032927,
+      "grad_norm": 0.47691431641578674,
+      "learning_rate": 0.0,
+      "loss": 1.3533,
+      "step": 30
+    },
+    {
+      "epoch": 0.03406187908032927,
+      "eval_loss": 1.303216814994812,
+      "eval_runtime": 14.7075,
+      "eval_samples_per_second": 25.225,
+      "eval_steps_per_second": 12.647,
+      "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": 2757139491717120.0,
+  "total_flos": 4135709237575680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null