Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3265667fbe625c76987b99b6d5f8de4a5c66a3c96489fb4acc58e1c6f49a65de
+oid sha256:f7f4e752979cdcca12c32b0aa81d08db0f264d88b3a7a665a1a936ac240243d9
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e627276dec8d39c421af06642f5c86139f015fcbea7f9a7ed3f95cb3a5668206
+oid sha256:d39ddcef2c82de05bd04a165aa17b7ffbbd618034f49a3e6b789e634e80ceb12
 size 261311226

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da70fcbf4bc000d633bdd59ff5bb75c3f527ccd5147f13a7552f0015370d4e68
+oid sha256:6aa91133351808aacad3e45f05aebdf1a2981ac4aa08431c95904a973b1b12d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2576157748699188,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016909744240118367,
+  "best_metric": 0.019720349460840225,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0033819488480236735,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 8.961,
       "eval_steps_per_second": 4.48,
       "step": 10
+    },
+    {
+      "epoch": 0.002029169308814204,
+      "grad_norm": 7.3718037605285645,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.0619,
+      "step": 12
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 1.747843623161316,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2561,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "eval_loss": 0.036673061549663544,
+      "eval_runtime": 277.2407,
+      "eval_samples_per_second": 8.981,
+      "eval_steps_per_second": 4.491,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030437539632213063,
+      "grad_norm": 1.052754521369934,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.116,
+      "step": 18
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "eval_loss": 0.019720349460840225,
+      "eval_runtime": 277.3036,
+      "eval_samples_per_second": 8.979,
+      "eval_steps_per_second": 4.49,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3272976912875520.0,
+  "total_flos": 6545953825751040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null