Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5e16014033de099b65fff0d904138813747f3820f86bdc60afe153cd8bfefb
+oid sha256:57b1ae45ac03e3207b09e1ac23b1e38858a524e8a0bd705a383961805599acae
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f3c0d7492e24b08a8a13d5a3c4dc14b8e0c96745fe77b7e80f65b639926c88
+oid sha256:463eeccfc78d309c1a49f2948019a8d230a3ee7c196629567eef061b6508af86
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb4b4628c52d803549c74c7105ecaa7cafbf93c22d4d51fbca8ee40bf7ccc43
+oid sha256:3afa84c0bce3bbe01a16966a0bcbfd31124726ca293ec2e783ca37b2ee587f9b
 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": 2.051936388015747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0032512395350727465,
+  "best_metric": 1.7570436000823975,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006502479070145493,
   "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": 16.265,
       "eval_steps_per_second": 4.068,
       "step": 10
+    },
+    {
+      "epoch": 0.003901487442087296,
+      "grad_norm": 2.0285325050354004,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.7677,
+      "step": 12
+    },
+    {
+      "epoch": 0.00487685930260912,
+      "grad_norm": 1.3885489702224731,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.6451,
+      "step": 15
+    },
+    {
+      "epoch": 0.00487685930260912,
+      "eval_loss": 1.8683792352676392,
+      "eval_runtime": 159.3475,
+      "eval_samples_per_second": 16.26,
+      "eval_steps_per_second": 4.067,
+      "step": 15
+    },
+    {
+      "epoch": 0.005852231163130944,
+      "grad_norm": 1.2759499549865723,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.6451,
+      "step": 18
+    },
+    {
+      "epoch": 0.006502479070145493,
+      "eval_loss": 1.7570436000823975,
+      "eval_runtime": 159.2372,
+      "eval_samples_per_second": 16.271,
+      "eval_steps_per_second": 4.069,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7860667205812224.0,
+  "total_flos": 1.5529610821238784e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null