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:fe7ecc831f6433cc578144208402e083789e82ce229544ecac3bf03ba65aa3f8
+oid sha256:64f1db8a415900a4c5e9b938bce7b68379f9af07de4c2eed33e11a9f9f096cbf
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b26f902d765ba7ebf55efe45190de96d537235d5309d5fed3329bacb36c0cd6c
+oid sha256:7b31196a69119be02df6378bad75ed14ca58e6f48be2e03ad87d6bc56717b878
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369bf5c6411c3e537b8c24723d05423e700e73e03b0e4c46b8b1bdc9f6c9ba24
+oid sha256:49cdcd980d63c40145ab4b6c85db4b1d946ad75a2654d6fbebb0bfc4d55072a9
 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": 2.132753849029541,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004050427826439168,
+  "best_metric": 2.127577781677246,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0060756417396587515,
   "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": 7.361,
       "eval_steps_per_second": 1.841,
       "step": 20
+    },
+    {
+      "epoch": 0.004252949217761126,
+      "grad_norm": 0.13068048655986786,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.0014,
+      "step": 21
+    },
+    {
+      "epoch": 0.004860513391727001,
+      "grad_norm": 0.15638871490955353,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.064,
+      "step": 24
+    },
+    {
+      "epoch": 0.005063034783048959,
+      "eval_loss": 2.1284475326538086,
+      "eval_runtime": 564.8508,
+      "eval_samples_per_second": 7.363,
+      "eval_steps_per_second": 1.841,
+      "step": 25
+    },
+    {
+      "epoch": 0.005468077565692876,
+      "grad_norm": 0.17189070582389832,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.0193,
+      "step": 27
+    },
+    {
+      "epoch": 0.0060756417396587515,
+      "grad_norm": 0.15045209228992462,
+      "learning_rate": 0.0,
+      "loss": 2.0982,
+      "step": 30
+    },
+    {
+      "epoch": 0.0060756417396587515,
+      "eval_loss": 2.127577781677246,
+      "eval_runtime": 564.334,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 1.843,
+      "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": 2.009383970852045e+16,
+  "total_flos": 2.662842172755149e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null