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:b0a4be6d8b4fab25bf607b5fd4f475dfafc78b3215ba48225d855224e1c9eb03
+oid sha256:a3741832c8bfc40419cc2b75425b5548fe1e890f08b1a7312a80bd5ad25c856b
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ff3db68a721441f9e0118ec05b71904fae162154a6c8fef202246f7b21f216
+oid sha256:c3e524c8affdef28e7ceaafee8b65a841b103f2f7bd5039ccfe0e8bbc97aa40d
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958222b24f79411664db3a748889ab6825f7305ef8dcb999fddd10d43e6507ad
+oid sha256:c002387a500d28b96422e2900466c710311455b171727616d355286a5ac4f48d
 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": 2.019080400466919,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.014270424545130217,
+  "best_metric": 1.9875426292419434,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.028540849090260435,
   "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": 4.271,
       "eval_steps_per_second": 1.071,
       "step": 10
+    },
+    {
+      "epoch": 0.01712450945415626,
+      "grad_norm": 0.788345217704773,
+      "learning_rate": 0.000163742398974869,
+      "loss": 8.3807,
+      "step": 12
+    },
+    {
+      "epoch": 0.021405636817695327,
+      "grad_norm": 0.5324597954750061,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.1896,
+      "step": 15
+    },
+    {
+      "epoch": 0.021405636817695327,
+      "eval_loss": 1.9932217597961426,
+      "eval_runtime": 138.9247,
+      "eval_samples_per_second": 4.247,
+      "eval_steps_per_second": 1.065,
+      "step": 15
+    },
+    {
+      "epoch": 0.025686764181234393,
+      "grad_norm": 0.4385243058204651,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 8.184,
+      "step": 18
+    },
+    {
+      "epoch": 0.028540849090260435,
+      "eval_loss": 1.9875426292419434,
+      "eval_runtime": 139.0154,
+      "eval_samples_per_second": 4.244,
+      "eval_steps_per_second": 1.065,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.306929288708096e+16,
+  "total_flos": 2.613858577416192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null