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:f1aaea344391ab4b4b6a0f82c7efe2ad6e70c99f588a3f97e458e6da91324c47
+oid sha256:f5a25258d99bed88450537d4e62ff4f7071b7120b4b0f6d5278b0f03ae4c564f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0206d3089bd8c72c575329e9f79f62bfd8c366944cebfd67fc18b2fcb13db36d
+oid sha256:748e501ddf5e9a31cebfc0d662294899a92ccceca5327d3fed7966151c9c85c2
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
 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": 3.032045841217041,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00012753881962822435,
+  "best_metric": 2.691340923309326,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0002550776392564487,
   "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": 7.686,
       "eval_steps_per_second": 3.843,
       "step": 10
+    },
+    {
+      "epoch": 0.0001530465835538692,
+      "grad_norm": 2.1459999084472656,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.9681,
+      "step": 12
+    },
+    {
+      "epoch": 0.0001913082294423365,
+      "grad_norm": 1.5466257333755493,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.8409,
+      "step": 15
+    },
+    {
+      "epoch": 0.0001913082294423365,
+      "eval_loss": 2.7555739879608154,
+      "eval_runtime": 4291.7816,
+      "eval_samples_per_second": 7.692,
+      "eval_steps_per_second": 3.846,
+      "step": 15
+    },
+    {
+      "epoch": 0.00022956987533080382,
+      "grad_norm": 1.3524450063705444,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.7526,
+      "step": 18
+    },
+    {
+      "epoch": 0.0002550776392564487,
+      "eval_loss": 2.691340923309326,
+      "eval_runtime": 4290.55,
+      "eval_samples_per_second": 7.695,
+      "eval_steps_per_second": 3.847,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709500842311680.0,
+  "total_flos": 7419001684623360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null