Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94731a28d4cabb72ba8e0a899d4ef50def15f6bb7979c144073092ea2134cb36
+oid sha256:c7f6e8ce994cf1365fd768b01d4613dcc69b8d5db5c1d58faaa6189d2c3a7f54
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa4f5fbdb13a7a5ac916ebb8b9795e9541295f4db674eaf2e59bc7db8189e5a
+oid sha256:f83022dc507644fb4a9581467c3878dfd0196a296df606b31e35197c933e986f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abb4e0455534bab038153dd7f744758ed8163ca01b3468e8fc62022a25f7a2c
+oid sha256:30b7ae4b206ae92b4259ffb923ef5da00009f3a53022d502c33431fc61393e52
 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": 0.5807424187660217,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0014304616815077067,
+  "best_metric": 0.5281378626823425,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0028609233630154133,
   "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": 4.436,
       "eval_steps_per_second": 2.218,
       "step": 10
+    },
+    {
+      "epoch": 0.0015735078496584773,
+      "grad_norm": 0.5131240487098694,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.5265,
+      "step": 11
+    },
+    {
+      "epoch": 0.001716554017809248,
+      "grad_norm": 0.5845620036125183,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.5663,
+      "step": 12
+    },
+    {
+      "epoch": 0.0018596001859600185,
+      "grad_norm": 0.7294037938117981,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7086,
+      "step": 13
+    },
+    {
+      "epoch": 0.002002646354110789,
+      "grad_norm": 0.7943013310432434,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6804,
+      "step": 14
+    },
+    {
+      "epoch": 0.0021456925222615598,
+      "grad_norm": 0.4809662997722626,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.4874,
+      "step": 15
+    },
+    {
+      "epoch": 0.0021456925222615598,
+      "eval_loss": 0.5374455451965332,
+      "eval_runtime": 648.85,
+      "eval_samples_per_second": 4.537,
+      "eval_steps_per_second": 2.269,
+      "step": 15
+    },
+    {
+      "epoch": 0.0022887386904123304,
+      "grad_norm": 0.5339108109474182,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6171,
+      "step": 16
+    },
+    {
+      "epoch": 0.002431784858563101,
+      "grad_norm": 0.4143908619880676,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.5623,
+      "step": 17
+    },
+    {
+      "epoch": 0.002574831026713872,
+      "grad_norm": 0.5520169138908386,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4427,
+      "step": 18
+    },
+    {
+      "epoch": 0.0027178771948646427,
+      "grad_norm": 0.4836729168891907,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5115,
+      "step": 19
+    },
+    {
+      "epoch": 0.0028609233630154133,
+      "grad_norm": 0.5311148166656494,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5827,
+      "step": 20
+    },
+    {
+      "epoch": 0.0028609233630154133,
+      "eval_loss": 0.5281378626823425,
+      "eval_runtime": 647.8029,
+      "eval_samples_per_second": 4.545,
+      "eval_steps_per_second": 2.272,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3190498328051712.0,
+  "total_flos": 6427235762307072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null