Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f65f25f8644122ab4ac3be8b777ae3e7789f5d12ccce2f341c55dbc49b2914e
+oid sha256:b0231b86cc713006c3c5996c2907e1295643250df0a35978260b20f654876056
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4de1e940fb6a38d4a9564f6b6d284b050032140494f4dbfd3cbedecdfaeb651
+oid sha256:b39bc52d57b13350b0e3b4a3c15c7bbd2ad9fb2d44e81c0f4bc4408340f0da66
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae91f747e28587ccb31e301b15e38431f4b25c5d16b3b7ce4c6bb44cc12bb99
+oid sha256:ddc46dafdcd478911a2d112b886f5f6b51a01f701c9711feedb0d870982ec3d6
 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": 1.6682432889938354,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.043149946062567425,
+  "best_metric": 1.27484130859375,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.08629989212513485,
   "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": 11.988,
       "eval_steps_per_second": 3.012,
       "step": 10
+    },
+    {
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.5690151453018188,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.5097,
+      "step": 12
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.6431310772895813,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3868,
+      "step": 15
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "eval_loss": 1.400833010673523,
+      "eval_runtime": 16.2816,
+      "eval_samples_per_second": 11.977,
+      "eval_steps_per_second": 3.01,
+      "step": 15
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.609404981136322,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.2746,
+      "step": 18
+    },
+    {
+      "epoch": 0.08629989212513485,
+      "eval_loss": 1.27484130859375,
+      "eval_runtime": 16.2697,
+      "eval_samples_per_second": 11.985,
+      "eval_steps_per_second": 3.012,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2695579394048e+16,
+  "total_flos": 2.5391158788096e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null