Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572a44df50931ba9b6e28f843bd0a479943a7c8926299433c6aedf3aeefcc0e2
+oid sha256:8d334bb443f4e33a32999eb4726befad36d86cb1890061f58902543bfe964457
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9372d0dbcf7010cd76b277c7a2b45ea9b25e2de212ffd9775eed437154517a0a
+oid sha256:f8c4dd0c87ca50d340509d31f50a19a77d55d9720a347dc1f6c5dccd89366170
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7647151947021484,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005028600163429505,
+  "best_metric": 0.7552729249000549,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.007542900245144258,
   "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": 11.809,
       "eval_steps_per_second": 5.908,
       "step": 20
+    },
+    {
+      "epoch": 0.005280030171600981,
+      "grad_norm": 0.28905293345451355,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.7918,
+      "step": 21
+    },
+    {
+      "epoch": 0.006034320196115406,
+      "grad_norm": 0.3992688059806824,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.7247,
+      "step": 24
+    },
+    {
+      "epoch": 0.006285750204286881,
+      "eval_loss": 0.759206235408783,
+      "eval_runtime": 141.8958,
+      "eval_samples_per_second": 11.804,
+      "eval_steps_per_second": 5.906,
+      "step": 25
+    },
+    {
+      "epoch": 0.006788610220629833,
+      "grad_norm": 0.3870250880718231,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.65,
+      "step": 27
+    },
+    {
+      "epoch": 0.007542900245144258,
+      "grad_norm": 0.38696086406707764,
+      "learning_rate": 0.0,
+      "loss": 0.7908,
+      "step": 30
+    },
+    {
+      "epoch": 0.007542900245144258,
+      "eval_loss": 0.7552729249000549,
+      "eval_runtime": 141.9468,
+      "eval_samples_per_second": 11.8,
+      "eval_steps_per_second": 5.904,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null