Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729adf03833058d23e03044cacdf645c575530b6ddb585ea732472921f755099
+oid sha256:b18b92685c7a6456b3fea5967d09af30d64df626f2356a0c55575a272ab6d41b
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d7469e6f6cd950a703525fe36d059d73f5f197692a87b1f25fcfd1d425cd376
+oid sha256:f30e16a9469e75bd54796b458ebaf072e73452a8a91d500a3a32df02c266314b
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f71a09c29af6bfe9e4bbb0a5dba46dd75c4bd315fc663a512155355f9b8a1a
+oid sha256:7d58d4ef710bb5bbbe3c8785ba2e5e671a4d3d656c4bf6bfe68b9e566becd2f4
 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": 1.2971845865249634,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.017738359201773836,
+  "best_metric": 0.9107561111450195,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.03547671840354767,
   "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": 7.203,
       "eval_steps_per_second": 3.602,
       "step": 10
+    },
+    {
+      "epoch": 0.01951219512195122,
+      "grad_norm": 1.956074833869934,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.3962,
+      "step": 11
+    },
+    {
+      "epoch": 0.021286031042128603,
+      "grad_norm": 1.7686818838119507,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.1724,
+      "step": 12
+    },
+    {
+      "epoch": 0.023059866962305987,
+      "grad_norm": 1.6020398139953613,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.0728,
+      "step": 13
+    },
+    {
+      "epoch": 0.02483370288248337,
+      "grad_norm": 1.6922051906585693,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.9902,
+      "step": 14
+    },
+    {
+      "epoch": 0.026607538802660754,
+      "grad_norm": 2.132755756378174,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.9552,
+      "step": 15
+    },
+    {
+      "epoch": 0.026607538802660754,
+      "eval_loss": 1.0003092288970947,
+      "eval_runtime": 34.7928,
+      "eval_samples_per_second": 6.84,
+      "eval_steps_per_second": 3.42,
+      "step": 15
+    },
+    {
+      "epoch": 0.028381374722838137,
+      "grad_norm": 1.8932487964630127,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0874,
+      "step": 16
+    },
+    {
+      "epoch": 0.03015521064301552,
+      "grad_norm": 2.181488037109375,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.0457,
+      "step": 17
+    },
+    {
+      "epoch": 0.031929046563192905,
+      "grad_norm": 2.006877899169922,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.0567,
+      "step": 18
+    },
+    {
+      "epoch": 0.03370288248337029,
+      "grad_norm": 1.926302433013916,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.9321,
+      "step": 19
+    },
+    {
+      "epoch": 0.03547671840354767,
+      "grad_norm": 1.6763228178024292,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.141,
+      "step": 20
+    },
+    {
+      "epoch": 0.03547671840354767,
+      "eval_loss": 0.9107561111450195,
+      "eval_runtime": 35.8064,
+      "eval_samples_per_second": 6.647,
+      "eval_steps_per_second": 3.323,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 240545515438080.0,
+  "total_flos": 481091030876160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null