Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43041e007db4ec55480a57ae31b20550e1c5e5a830df996dfb19101e144f6e5c
+oid sha256:69fee2e3151b208f0428e64da587da6c664ae0f90ed3d4a5fa23d54c44708a0b
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff190ded7d7ce39726960b3edb6278949f9fa268cf36e90836033edbdc36f26
+oid sha256:6ab875c9ea2eba406ddb487cbc40910cd3c06a07ea8185bf961546bc06b908e2
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2866d9daac23f6f19f9103083dea4ac4ce2c947ea159533bcbfccccda0ee4b64
+oid sha256:91e127c5735f592030883226bb7e6212829e90bdab82288e432cba0360369d53
 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": 2.1212799549102783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008595680670463093,
+  "best_metric": 0.9566317796707153,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0017191361340926185,
   "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": 5.524,
       "eval_steps_per_second": 2.762,
       "step": 10
+    },
+    {
+      "epoch": 0.0009455248737509402,
+      "grad_norm": 17.285173416137695,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 9.1643,
+      "step": 11
+    },
+    {
+      "epoch": 0.0010314816804555711,
+      "grad_norm": 20.7039852142334,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 7.2011,
+      "step": 12
+    },
+    {
+      "epoch": 0.001117438487160202,
+      "grad_norm": 15.796852111816406,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.0756,
+      "step": 13
+    },
+    {
+      "epoch": 0.001203395293864833,
+      "grad_norm": 13.192728042602539,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 5.4776,
+      "step": 14
+    },
+    {
+      "epoch": 0.001289352100569464,
+      "grad_norm": 16.307395935058594,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 6.4935,
+      "step": 15
+    },
+    {
+      "epoch": 0.001289352100569464,
+      "eval_loss": 1.2589789628982544,
+      "eval_runtime": 919.1048,
+      "eval_samples_per_second": 5.33,
+      "eval_steps_per_second": 2.666,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013753089072740948,
+      "grad_norm": 23.68831443786621,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.7626,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014612657139787258,
+      "grad_norm": 12.60560417175293,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.5314,
+      "step": 17
+    },
+    {
+      "epoch": 0.0015472225206833567,
+      "grad_norm": 16.297088623046875,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 5.5915,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016331793273879876,
+      "grad_norm": 11.184680938720703,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.0509,
+      "step": 19
+    },
+    {
+      "epoch": 0.0017191361340926185,
+      "grad_norm": 16.991424560546875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.8412,
+      "step": 20
+    },
+    {
+      "epoch": 0.0017191361340926185,
+      "eval_loss": 0.9566317796707153,
+      "eval_runtime": 913.3504,
+      "eval_samples_per_second": 5.364,
+      "eval_steps_per_second": 2.682,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 298765642629120.0,
+  "total_flos": 597531285258240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null