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:cfb36332021ac46391fa280f3417af3027f81986f097ee16bef1e34efd29f2f5
+oid sha256:82c44e4554c5b33e28a3a7c8db9cfc70b42b00730d94d67b54be464358f688f9
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cc21f138eab64a264fdb78496e54255c3fcab317b34b0d76a0cc1ef2040955
+oid sha256:21df5c0c050d7d7f074ebd6a9cef34cbdc03ade57d7ff7b53c89ef46631d4f20
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c382e7c8713d276519a4a5874bff029b5cf569c6726e9909b28422efc294085e
+oid sha256:429e821de81d4cee50fc3cb875c538119e796c0a8cbb3f0de05348377209f39d
 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": 10.65870475769043,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.013395847287340924,
+  "best_metric": 10.61253547668457,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.020093770931011386,
   "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": 176.184,
       "eval_steps_per_second": 88.232,
       "step": 20
+    },
+    {
+      "epoch": 0.01406563965170797,
+      "grad_norm": 4.6402482986450195,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 42.7916,
+      "step": 21
+    },
+    {
+      "epoch": 0.016075016744809108,
+      "grad_norm": 4.53489351272583,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 42.5776,
+      "step": 24
+    },
+    {
+      "epoch": 0.016744809109176157,
+      "eval_loss": 10.620636940002441,
+      "eval_runtime": 3.5829,
+      "eval_samples_per_second": 175.558,
+      "eval_steps_per_second": 87.919,
+      "step": 25
+    },
+    {
+      "epoch": 0.01808439383791025,
+      "grad_norm": 4.104396820068359,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 42.4821,
+      "step": 27
+    },
+    {
+      "epoch": 0.020093770931011386,
+      "grad_norm": 4.393144607543945,
+      "learning_rate": 0.0,
+      "loss": 42.4139,
+      "step": 30
+    },
+    {
+      "epoch": 0.020093770931011386,
+      "eval_loss": 10.61253547668457,
+      "eval_runtime": 3.5693,
+      "eval_samples_per_second": 176.223,
+      "eval_steps_per_second": 88.252,
+      "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": 415991070720.0,
+  "total_flos": 623986606080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null