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:aaa087fc83568a11c607f32bc2707a8c70f97da6d9a3ef99e9d0960800b3994d
+oid sha256:b19a052a9e33e0b3f465c4b945c093c238936c223dee687471936422e9d6dfb0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d972ba6ced0f7c8cfaada939c4b2621ec705a5d47e280a30aaba93115321d631
+oid sha256:5f158b1f591aa5624099ce867dcece07e7910ed2fc73413dcf222c0cdf2af597
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
 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": 1.8860292434692383,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005243494789277053,
+  "best_metric": 1.8007258176803589,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0010486989578554107,
   "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": 7.745,
       "eval_steps_per_second": 3.873,
       "step": 10
+    },
+    {
+      "epoch": 0.0006292193747132464,
+      "grad_norm": 1.200909972190857,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.8616,
+      "step": 12
+    },
+    {
+      "epoch": 0.000786524218391558,
+      "grad_norm": 1.3885806798934937,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.8103,
+      "step": 15
+    },
+    {
+      "epoch": 0.000786524218391558,
+      "eval_loss": 1.8279458284378052,
+      "eval_runtime": 1036.8048,
+      "eval_samples_per_second": 7.745,
+      "eval_steps_per_second": 3.872,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009438290620698696,
+      "grad_norm": 1.2335426807403564,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.9141,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010486989578554107,
+      "eval_loss": 1.8007258176803589,
+      "eval_runtime": 1032.7061,
+      "eval_samples_per_second": 7.776,
+      "eval_steps_per_second": 3.888,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null