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:ef78469dd136fde6e6bb349513c127297486bb27a467676a76603bab3c833cfb
+oid sha256:1a0df98cb00c640ab5f6f7c4171ad91ef881c6de8f83e7b9b46460da50e1b3d3
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a9916a942364c2a999f1f5fa4eead4a5b289212ba156ab840e824de49bdfe6
+oid sha256:82900ef48859f9a2d4305c782eb041590dca485a8a71c4dc2d28187c368c54f4
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955f9b71dcac41cc20ba50f33f5f94d5c327a3e44c061530795b4cfdaec4edee
+oid sha256:11f9ffa98442fbbee6ee9de7d29453165f8790f6b43ee3f31090479489c66cf6
 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": 10.376076698303223,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00366905155017428,
+  "best_metric": 10.375173568725586,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00733810310034856,
   "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": 443.068,
       "eval_steps_per_second": 110.767,
       "step": 10
+    },
+    {
+      "epoch": 0.004402861860209136,
+      "grad_norm": 0.01696758158504963,
+      "learning_rate": 0.000163742398974869,
+      "loss": 10.376,
+      "step": 12
+    },
+    {
+      "epoch": 0.00550357732526142,
+      "grad_norm": 0.019351821392774582,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3757,
+      "step": 15
+    },
+    {
+      "epoch": 0.00550357732526142,
+      "eval_loss": 10.375539779663086,
+      "eval_runtime": 5.2474,
+      "eval_samples_per_second": 437.548,
+      "eval_steps_per_second": 109.387,
+      "step": 15
+    },
+    {
+      "epoch": 0.006604292790313704,
+      "grad_norm": 0.016618570312857628,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 10.3744,
+      "step": 18
+    },
+    {
+      "epoch": 0.00733810310034856,
+      "eval_loss": 10.375173568725586,
+      "eval_runtime": 5.1303,
+      "eval_samples_per_second": 447.539,
+      "eval_steps_per_second": 111.885,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 523024465920.0,
+  "total_flos": 1046048931840.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null