Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4b6c052c3982266b03230a8522f868e75fa902017833307a21b9c5c41c2dbb
+oid sha256:9e0c5a1602c3d16d8405770934fa28e60780b2798198d6076eccb41cd0d8e030
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cbab540eb9e44882b260cfe41d26a4debeb1c2b7b39f347a784124aef489d4
+oid sha256:f6186f2e036037ba510ad58dc1026f153b17136aac0395bddf11df59c98a5ee8
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ceca0a03a6c8b9bafc5ccbda6d8e320bbdebb9ac3a5e7de57763c2ca936a4b4
+oid sha256:541377d76f1bc1fd25990942ced30944fbf4312d9f4296baaf548ac2eb683bfa
 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": 1.4723725318908691,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.01689902830587241,
+  "best_metric": 1.2771832942962646,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.03379805661174482,
   "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": 10.981,
       "eval_steps_per_second": 5.491,
       "step": 10
+    },
+    {
+      "epoch": 0.018588931136459652,
+      "grad_norm": 1.509872555732727,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.4891,
+      "step": 11
+    },
+    {
+      "epoch": 0.020278833967046894,
+      "grad_norm": 1.6094928979873657,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.6946,
+      "step": 12
+    },
+    {
+      "epoch": 0.021968736797634135,
+      "grad_norm": 1.5100297927856445,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.5713,
+      "step": 13
+    },
+    {
+      "epoch": 0.023658639628221376,
+      "grad_norm": 1.6203187704086304,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.7319,
+      "step": 14
+    },
+    {
+      "epoch": 0.025348542458808618,
+      "grad_norm": 1.366817593574524,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1443,
+      "step": 15
+    },
+    {
+      "epoch": 0.025348542458808618,
+      "eval_loss": 1.325199007987976,
+      "eval_runtime": 23.2566,
+      "eval_samples_per_second": 10.75,
+      "eval_steps_per_second": 5.375,
+      "step": 15
+    },
+    {
+      "epoch": 0.02703844528939586,
+      "grad_norm": 1.5522985458374023,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2413,
+      "step": 16
+    },
+    {
+      "epoch": 0.0287283481199831,
+      "grad_norm": 1.5510913133621216,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.2517,
+      "step": 17
+    },
+    {
+      "epoch": 0.030418250950570342,
+      "grad_norm": 1.658223271369934,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.4299,
+      "step": 18
+    },
+    {
+      "epoch": 0.03210815378115758,
+      "grad_norm": 2.0415923595428467,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.44,
+      "step": 19
+    },
+    {
+      "epoch": 0.03379805661174482,
+      "grad_norm": 1.5060479640960693,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.1204,
+      "step": 20
+    },
+    {
+      "epoch": 0.03379805661174482,
+      "eval_loss": 1.2771832942962646,
+      "eval_runtime": 26.3745,
+      "eval_samples_per_second": 9.479,
+      "eval_steps_per_second": 4.739,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 370898368462848.0,
+  "total_flos": 709822739644416.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null