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:c47ab604219b95a710538269ff3e2c4c10ade2bf23915529145fe4806f152769
+oid sha256:f8c4968c672670a06883e83bd5392eae53f5a037c822904fa009b8b4372a9507
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c814b8298fdf84eefc9c579d43b3edcc5acedf28ee50e093eaca4775b3051705
+oid sha256:b259ba46e7099a298017da5718c8823f5c8ef2c0ac895cd6dd97e80cb05d8078
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:4e336ffb4f2385fe7817a79ed4d3cfcc71e6b65eaf2fdf9bb2447eedac0e09f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3134835958480835,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004243581582855931,
+  "best_metric": 1.1928067207336426,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.008487163165711862,
   "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": 7.657,
       "eval_steps_per_second": 3.833,
       "step": 10
+    },
+    {
+      "epoch": 0.005092297899427116,
+      "grad_norm": 0.7152264714241028,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.3058,
+      "step": 12
+    },
+    {
+      "epoch": 0.006365372374283896,
+      "grad_norm": 0.5883220434188843,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.2339,
+      "step": 15
+    },
+    {
+      "epoch": 0.006365372374283896,
+      "eval_loss": 1.2224185466766357,
+      "eval_runtime": 129.5429,
+      "eval_samples_per_second": 7.665,
+      "eval_steps_per_second": 3.837,
+      "step": 15
+    },
+    {
+      "epoch": 0.0076384468491406746,
+      "grad_norm": 0.6324528455734253,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.1509,
+      "step": 18
+    },
+    {
+      "epoch": 0.008487163165711862,
+      "eval_loss": 1.1928067207336426,
+      "eval_runtime": 129.2663,
+      "eval_samples_per_second": 7.682,
+      "eval_steps_per_second": 3.845,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7511608746049536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null