Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e464a3bbe52b949168e708676cb441625e8c1fa2117d34141ea15e3634a445
+oid sha256:dea4b7976ba6cc61571f2332740282f3b16fd9afa7e849a976c102e1728e14a4
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:262295db875ec1922efa03595f66493f78ae0aa6f558f4f8ec19a2808d5516bb
+oid sha256:1dfa39e0335ccdf1182e3407ba30c3a4b25237199632d6f494ad3084d51b9690
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d317c8c136dbfaa7d00b3b636a57f9087e0cc72926988c2be1ed6398941542ca
+oid sha256:e795150f6ce7fa12ee4e6e03a761abfdca9e4c5647c2b5c8b15eb7fe34e24b61
 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": 4.860773086547852,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008481764206955046,
+  "best_metric": 4.792747497558594,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.016963528413910092,
   "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": 23.258,
       "eval_steps_per_second": 5.832,
       "step": 10
+    },
+    {
+      "epoch": 0.010178117048346057,
+      "grad_norm": 0.13161055743694305,
+      "learning_rate": 0.000163742398974869,
+      "loss": 4.8411,
+      "step": 12
+    },
+    {
+      "epoch": 0.01272264631043257,
+      "grad_norm": 0.14220638573169708,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.8331,
+      "step": 15
+    },
+    {
+      "epoch": 0.01272264631043257,
+      "eval_loss": 4.81943416595459,
+      "eval_runtime": 42.6958,
+      "eval_samples_per_second": 23.258,
+      "eval_steps_per_second": 5.832,
+      "step": 15
+    },
+    {
+      "epoch": 0.015267175572519083,
+      "grad_norm": 0.12289228290319443,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 4.8002,
+      "step": 18
+    },
+    {
+      "epoch": 0.016963528413910092,
+      "eval_loss": 4.792747497558594,
+      "eval_runtime": 42.6653,
+      "eval_samples_per_second": 23.274,
+      "eval_steps_per_second": 5.836,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2610106655047680.0,
+  "total_flos": 5220213310095360.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null