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:fc68d3e231378c66765970b6f98aebf0dce0531ee50173c1cac0e3ffcbd108b3
+oid sha256:387b42ce73f98c6f56eaf84a5a10379cd888ab6fcf6a3e45d3bfff7c5af8533f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59aa9b2e3f461052cc3fb310a4251e1a685b2527e4cb2688a29e307bbf82be51
+oid sha256:51caf9057f278c0fab913c487ca40a280fa244b4c512cff11399bfb65d2a8829
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5135bffbd46bbc30233eefc023d5d36ab37a285f9c2d22de6fd4bb055926ae2
+oid sha256:a0c817fa4491c1f235ed2813fa2e590ac303ad5ecf9c704186329c6fe865a48c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da9db9fb6671f70d2a4e7001f6523f325b24520bef80a5a7ba3fc8703a924b
+oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9088382720947266,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001862370798025887,
+  "best_metric": 1.8506921529769897,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0027935561970388306,
   "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": 17.015,
       "eval_steps_per_second": 4.254,
       "step": 20
+    },
+    {
+      "epoch": 0.0019554893379271814,
+      "grad_norm": 0.8892120122909546,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 1.5314,
+      "step": 21
+    },
+    {
+      "epoch": 0.0022348449576310644,
+      "grad_norm": 1.0052318572998047,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 1.5404,
+      "step": 24
+    },
+    {
+      "epoch": 0.002327963497532359,
+      "eval_loss": 1.8609997034072876,
+      "eval_runtime": 530.1572,
+      "eval_samples_per_second": 17.059,
+      "eval_steps_per_second": 4.265,
+      "step": 25
+    },
+    {
+      "epoch": 0.0025142005773349475,
+      "grad_norm": 1.1246418952941895,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 1.5776,
+      "step": 27
+    },
+    {
+      "epoch": 0.0027935561970388306,
+      "grad_norm": 1.5440231561660767,
+      "learning_rate": 0.0,
+      "loss": 1.7174,
+      "step": 30
+    },
+    {
+      "epoch": 0.0027935561970388306,
+      "eval_loss": 1.8506921529769897,
+      "eval_runtime": 530.694,
+      "eval_samples_per_second": 17.042,
+      "eval_steps_per_second": 4.26,
+      "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": 1.831068605664461e+16,
+  "total_flos": 2.570894304922829e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null