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:d617d4d58dc46befd32106b7f40317c4c334e5244c256773914ea0021e48ab75
+oid sha256:72098449a12da2a4d2523a3801e6a56e6f96df52174200bf500fa0d320c70d33
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a192f88399cdc45a128fe2b1aa465f0b3fcab3c999777924bee7cfd84007a357
+oid sha256:59779e80b483fc64f2d90596c469baeae51d5d6476d8f59455c5a29e2aae1966
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c82987d4b0b404e9f3e5800cb851981f4fe776fce1b2b553d4114b981aa39de
+oid sha256:3fc6907f743e6ade7fc1243ae57f0164bc03b3d79b91c8558b2c0c9f954362e9
 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": 1.0624722242355347,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02909090909090909,
+  "best_metric": 1.0438560247421265,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.04363636363636364,
   "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": 4.123,
       "eval_steps_per_second": 2.062,
       "step": 20
+    },
+    {
+      "epoch": 0.030545454545454546,
+      "grad_norm": 0.9544651508331299,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.9652,
+      "step": 21
+    },
+    {
+      "epoch": 0.03490909090909091,
+      "grad_norm": 1.1931819915771484,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.0406,
+      "step": 24
+    },
+    {
+      "epoch": 0.03636363636363636,
+      "eval_loss": 1.0489847660064697,
+      "eval_runtime": 69.585,
+      "eval_samples_per_second": 4.168,
+      "eval_steps_per_second": 2.084,
+      "step": 25
+    },
+    {
+      "epoch": 0.03927272727272727,
+      "grad_norm": 0.9869446158409119,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.9518,
+      "step": 27
+    },
+    {
+      "epoch": 0.04363636363636364,
+      "grad_norm": 1.1711513996124268,
+      "learning_rate": 0.0,
+      "loss": 1.04,
+      "step": 30
+    },
+    {
+      "epoch": 0.04363636363636364,
+      "eval_loss": 1.0438560247421265,
+      "eval_runtime": 69.4905,
+      "eval_samples_per_second": 4.173,
+      "eval_steps_per_second": 2.087,
+      "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": 8687386695303168.0,
+  "total_flos": 1.2925136302768128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null