Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8141df69b16b9d554151c0fdfa47713eded1e2072dc1fc6bac7af3120c383af7
+oid sha256:adcf1be019a295830709b0447cadbcbebd30cabce308ff7114f9ed19aee608d7
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab381c8301a65c7a48d5cb7bb3bae6fddcd4f443c9b39f1d93c6d1b9c0a0d31
+oid sha256:2da77999fbad23a12b26a1bdeee4610518670b441ab8f59599dbb222572890bd
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1008eff30b09a4a1eae67b46948ddbde84beca9125d6695fa958e5e1151894e4
+oid sha256:094210e52f7ab6005271dd83568f1e6f314005e45196b10710db6e1b54b3ad67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.091917037963867,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00045196718718221055,
+  "best_metric": 11.087591171264648,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0009039343743644211,
   "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": 52.896,
       "eval_steps_per_second": 26.451,
       "step": 10
+    },
+    {
+      "epoch": 0.0004971639059004316,
+      "grad_norm": 0.7067858576774597,
+      "learning_rate": 0.0001999979446958366,
+      "loss": 44.3933,
+      "step": 11
+    },
+    {
+      "epoch": 0.0005423606246186527,
+      "grad_norm": 0.7694055438041687,
+      "learning_rate": 0.00019999177886783194,
+      "loss": 44.3476,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005875573433368737,
+      "grad_norm": 0.6980550289154053,
+      "learning_rate": 0.00019998150276943902,
+      "loss": 44.3621,
+      "step": 13
+    },
+    {
+      "epoch": 0.0006327540620550948,
+      "grad_norm": 0.7399426698684692,
+      "learning_rate": 0.000199967116823068,
+      "loss": 44.3727,
+      "step": 14
+    },
+    {
+      "epoch": 0.0006779507807733159,
+      "grad_norm": 0.6623771786689758,
+      "learning_rate": 0.0001999486216200688,
+      "loss": 44.3563,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006779507807733159,
+      "eval_loss": 11.089905738830566,
+      "eval_runtime": 176.0326,
+      "eval_samples_per_second": 52.928,
+      "eval_steps_per_second": 26.467,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007231474994915369,
+      "grad_norm": 0.6647756695747375,
+      "learning_rate": 0.00019992601792070679,
+      "loss": 44.3454,
+      "step": 16
+    },
+    {
+      "epoch": 0.000768344218209758,
+      "grad_norm": 0.7416101694107056,
+      "learning_rate": 0.00019989930665413147,
+      "loss": 44.3249,
+      "step": 17
+    },
+    {
+      "epoch": 0.0008135409369279791,
+      "grad_norm": 0.6351829171180725,
+      "learning_rate": 0.00019986848891833845,
+      "loss": 44.37,
+      "step": 18
+    },
+    {
+      "epoch": 0.0008587376556462001,
+      "grad_norm": 0.6839431524276733,
+      "learning_rate": 0.0001998335659801241,
+      "loss": 44.3472,
+      "step": 19
+    },
+    {
+      "epoch": 0.0009039343743644211,
+      "grad_norm": 0.6762228608131409,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 44.3507,
+      "step": 20
+    },
+    {
+      "epoch": 0.0009039343743644211,
+      "eval_loss": 11.087591171264648,
+      "eval_runtime": 176.1534,
+      "eval_samples_per_second": 52.891,
+      "eval_steps_per_second": 26.449,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 105067315200.0,
+  "total_flos": 210134630400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null