Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a69f6c42576c41ad4e3ece1beb01ba94e63e02c39cb365943058d1a6f537d64
+oid sha256:72117ac5f9bf7ebb1701fb6715c32d81e70c9ebb45138961d4749a2d954cddd9
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66fa701cc0336b5a114aec85fa5e22fc80b6d5e984b85798c868bc6ebb3d31ae
+oid sha256:9feaca09ec00e3e5b1d5b633518b7d35674477b62531edc903f48064743aee37
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b61af08a0b49ae3026e06f03c7aca5bd6e1a70a6b11fae1c6577f930cbe4e6d2
+oid sha256:7bd082d426c5a2595f03a243a16789fbf4f16702371fd453403159dbedd3e918
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6607580184936523,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00024053784261608956,
+  "best_metric": 1.9420759677886963,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00048107568523217913,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 15.678,
       "eval_steps_per_second": 3.92,
       "step": 10
+    },
+    {
+      "epoch": 0.00028864541113930747,
+      "grad_norm": 6.304234504699707,
+      "learning_rate": 0.000163742398974869,
+      "loss": 8.3158,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003608067639241344,
+      "grad_norm": 10.350303649902344,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.6677,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003608067639241344,
+      "eval_loss": 2.1993517875671387,
+      "eval_runtime": 2232.9143,
+      "eval_samples_per_second": 15.679,
+      "eval_steps_per_second": 3.92,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004329681167089612,
+      "grad_norm": 6.310632228851318,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 7.355,
+      "step": 18
+    },
+    {
+      "epoch": 0.00048107568523217913,
+      "eval_loss": 1.9420759677886963,
+      "eval_runtime": 2232.9801,
+      "eval_samples_per_second": 15.679,
+      "eval_steps_per_second": 3.92,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6534646443540480.0,
+  "total_flos": 1.306929288708096e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null