Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7f8a664e76becbd6c3bfecc6d6e3d3a9842a66460d04de1bb6a1cd8a085e6a
+oid sha256:35d5969715fef1bffd27874c51d4ba8110f059dec0dc5d228d43441f6e9057cf
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd41aad3f1edb0c0019e944dab1ac609b214a0bb24814c22501033dbac47ab4
+oid sha256:b56fcb8c31ebefa935300c7978f9516f9b034db13992b3df30d3ffac2752592e
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa382952e0adbb7e7abb917278c0a70d8bfd97851369da627797b4983c8f9cb6
+oid sha256:c7c1700cb1f556e4bf9f478fe45a08f379817072e65ab986da440073e77a1831
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2191153764724731,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00134707348285849,
+  "best_metric": 1.157989501953125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00269414696571698,
   "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": 2.789,
       "eval_steps_per_second": 1.394,
       "step": 10
+    },
+    {
+      "epoch": 0.0016164881794301878,
+      "grad_norm": 0.7936702966690063,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 4.7597,
+      "step": 12
+    },
+    {
+      "epoch": 0.002020610224287735,
+      "grad_norm": 1.5666340589523315,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.6971,
+      "step": 15
+    },
+    {
+      "epoch": 0.002020610224287735,
+      "eval_loss": 1.1779574155807495,
+      "eval_runtime": 1121.3367,
+      "eval_samples_per_second": 2.788,
+      "eval_steps_per_second": 1.394,
+      "step": 15
+    },
+    {
+      "epoch": 0.0024247322691452818,
+      "grad_norm": 0.8135265111923218,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 4.4632,
+      "step": 18
+    },
+    {
+      "epoch": 0.00269414696571698,
+      "eval_loss": 1.157989501953125,
+      "eval_runtime": 1121.0708,
+      "eval_samples_per_second": 2.788,
+      "eval_steps_per_second": 1.394,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2695579394048e+16,
+  "total_flos": 2.5391158788096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null