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:c9de8d7bbf7f5ae796e7f29f961988dc3cea507b9bc591a5a5b00f078f0c48fb
+oid sha256:dd17faa28b705c00725ed94ca7e640238d5f8156d9688eef6307db3c8644c7c4
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38dfa35193cbbd1625fcc5003c58892e0208fb27de3f884d38010617865fe0b0
+oid sha256:bef34617dadb4f71f9fd15ec4102ccda16f2d0c01761e6c5e57fcd2bb402a601
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22cc4a9a02a6f74d668e9df70ad462220b16b60af37292d30446f2a841cfc377
+oid sha256:bcf7798404e1bc6a3d9600a9f3df20469c8b23af137a19e5bc32db3bc281bffc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6886987686157227,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016909744240118367,
+  "best_metric": 0.6605696082115173,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0033819488480236735,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 8.465,
       "eval_steps_per_second": 4.233,
       "step": 10
+    },
+    {
+      "epoch": 0.0018600718664130206,
+      "grad_norm": 0.45267313718795776,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7075,
+      "step": 11
+    },
+    {
+      "epoch": 0.002029169308814204,
+      "grad_norm": 0.44445890188217163,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7202,
+      "step": 12
+    },
+    {
+      "epoch": 0.002198266751215388,
+      "grad_norm": 0.4871218502521515,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.6876,
+      "step": 13
+    },
+    {
+      "epoch": 0.0023673641936165714,
+      "grad_norm": 0.4805002212524414,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.698,
+      "step": 14
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 0.5254651308059692,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6566,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "eval_loss": 0.6768798828125,
+      "eval_runtime": 296.3003,
+      "eval_samples_per_second": 8.404,
+      "eval_steps_per_second": 4.202,
+      "step": 15
+    },
+    {
+      "epoch": 0.002705559078418939,
+      "grad_norm": 0.5989558100700378,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6743,
+      "step": 16
+    },
+    {
+      "epoch": 0.0028746565208201224,
+      "grad_norm": 0.5035123229026794,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.8069,
+      "step": 17
+    },
+    {
+      "epoch": 0.0030437539632213063,
+      "grad_norm": 0.5071959495544434,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.6762,
+      "step": 18
+    },
+    {
+      "epoch": 0.00321285140562249,
+      "grad_norm": 0.4506031572818756,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5849,
+      "step": 19
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "grad_norm": 0.4659384787082672,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6887,
+      "step": 20
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "eval_loss": 0.6605696082115173,
+      "eval_runtime": 295.6071,
+      "eval_samples_per_second": 8.423,
+      "eval_steps_per_second": 4.212,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 173624419418112.0,
+  "total_flos": 351700747026432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null