Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ebfc1750954f0ec2c0a3ce593d9f1025456c5203b802dc62d687a6f97e628c4
+oid sha256:97dde84aca5e345c587a93bc6e24b31f237066002e847b5013fd441cd4009df7
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21899417fa22da2360473e9d9ffea4c279786365d9e9d28948e346716f9052d4
+oid sha256:9cbbd016dad5b7183959f33fc7f155012ccb7c77343d42fdc2fb54a980b1c615
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565c117b0554bcadbb2962d5778f478da838b047d26cc08e6b3663c916f71fed
+oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
 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": 2.9601454734802246,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011431837667905115,
+  "best_metric": 2.4806277751922607,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.02286367533581023,
   "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": 5.37,
       "eval_steps_per_second": 2.693,
       "step": 10
+    },
+    {
+      "epoch": 0.012575021434695627,
+      "grad_norm": 9.215521812438965,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 11.6118,
+      "step": 11
+    },
+    {
+      "epoch": 0.01371820520148614,
+      "grad_norm": 10.720466613769531,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 11.387,
+      "step": 12
+    },
+    {
+      "epoch": 0.014861388968276651,
+      "grad_norm": 9.58012866973877,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 12.0335,
+      "step": 13
+    },
+    {
+      "epoch": 0.01600457273506716,
+      "grad_norm": 8.0549955368042,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 11.5604,
+      "step": 14
+    },
+    {
+      "epoch": 0.017147756501857674,
+      "grad_norm": 6.788261413574219,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 11.255,
+      "step": 15
+    },
+    {
+      "epoch": 0.017147756501857674,
+      "eval_loss": 2.5551671981811523,
+      "eval_runtime": 67.9449,
+      "eval_samples_per_second": 5.431,
+      "eval_steps_per_second": 2.723,
+      "step": 15
+    },
+    {
+      "epoch": 0.018290940268648186,
+      "grad_norm": 6.838973522186279,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.1901,
+      "step": 16
+    },
+    {
+      "epoch": 0.019434124035438698,
+      "grad_norm": 8.572029113769531,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 10.9187,
+      "step": 17
+    },
+    {
+      "epoch": 0.02057730780222921,
+      "grad_norm": 11.447615623474121,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 10.5933,
+      "step": 18
+    },
+    {
+      "epoch": 0.021720491569019718,
+      "grad_norm": 11.014549255371094,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 12.2246,
+      "step": 19
+    },
+    {
+      "epoch": 0.02286367533581023,
+      "grad_norm": 10.644768714904785,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 9.7867,
+      "step": 20
+    },
+    {
+      "epoch": 0.02286367533581023,
+      "eval_loss": 2.4806277751922607,
+      "eval_runtime": 67.9043,
+      "eval_samples_per_second": 5.434,
+      "eval_steps_per_second": 2.724,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166224305356800.0,
+  "total_flos": 6332448610713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null