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:b1d24ecaf737b0f11aafe2b0c7c0a0924b63ae99e3eaa43be667dff31e6ff9f8
+oid sha256:f147fd2d4daf4632bb9fdf29d617019084b5284c568613dd597773fdff4901da
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b7dfd84d797a3309c122f72a81848b279dc7c41fdc21837441dd95320bfbc6
+oid sha256:dcbdba99b34caf538cdd330838bef22d617e9f47539acdd8e8bcb08ea40ff46e
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16998bdba1644829794d37ef38dae81ca1e362a0ac333e8cc69acc47aafd2361
+oid sha256:faf4edccebbc69cd5a7d67b6fb128ea8405dd99d3ea114f7f7b9f353128a6c14
 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": 1.1640980243682861,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.05108556832694764,
+  "best_metric": 1.122968316078186,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.10217113665389528,
   "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": 3.848,
       "eval_steps_per_second": 0.98,
       "step": 10
+    },
+    {
+      "epoch": 0.06130268199233716,
+      "grad_norm": 0.1395108997821808,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.9864,
+      "step": 12
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "grad_norm": 0.14121867716312408,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.985,
+      "step": 15
+    },
+    {
+      "epoch": 0.07662835249042145,
+      "eval_loss": 1.148338794708252,
+      "eval_runtime": 41.99,
+      "eval_samples_per_second": 3.93,
+      "eval_steps_per_second": 1.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.13990887999534607,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.9709,
+      "step": 18
+    },
+    {
+      "epoch": 0.10217113665389528,
+      "eval_loss": 1.122968316078186,
+      "eval_runtime": 44.6271,
+      "eval_samples_per_second": 3.697,
+      "eval_steps_per_second": 0.941,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.061869578092544e+16,
+  "total_flos": 1.715327779995648e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null