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:f267f29e15462f8df86cc6a6c599cc5eed785d3fc6d59eb92664515ae0f4533e
+oid sha256:2858ae17c9e809160fd4c780130d7cbdb9ff665c42d06916ca31186217320c90
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9c7699767a1c4f8f26c9b9facadf497cd2c652ef1b5e4ebe982c14f04ec37f
+oid sha256:96a76e1c96071186254679eb95135d535b279ca9d37f6e14f5a73804622723d2
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9610731ac1a29e8e416ad43f449b8d757d6ef531a6353e37c7518551ca6b27fd
+oid sha256:6c10616b6db17724e17846972facdd56debf0a71a5f856a8d9161a9eb54673cf
 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": 1.0314421653747559,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005651313930488839,
+  "best_metric": 0.8038806915283203,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.011302627860977677,
   "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": 2.129,
       "eval_steps_per_second": 0.533,
       "step": 10
+    },
+    {
+      "epoch": 0.006781576716586606,
+      "grad_norm": 0.2585771381855011,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.9694,
+      "step": 12
+    },
+    {
+      "epoch": 0.008476970895733259,
+      "grad_norm": 0.1790218949317932,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9023,
+      "step": 15
+    },
+    {
+      "epoch": 0.008476970895733259,
+      "eval_loss": 0.8702918291091919,
+      "eval_runtime": 700.0949,
+      "eval_samples_per_second": 2.128,
+      "eval_steps_per_second": 0.533,
+      "step": 15
+    },
+    {
+      "epoch": 0.010172365074879909,
+      "grad_norm": 0.14580154418945312,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.8086,
+      "step": 18
+    },
+    {
+      "epoch": 0.011302627860977677,
+      "eval_loss": 0.8038806915283203,
+      "eval_runtime": 697.027,
+      "eval_samples_per_second": 2.138,
+      "eval_steps_per_second": 0.535,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.53296434479104e+16,
+  "total_flos": 5.06592868958208e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null