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:d5e2782400dbe2383112cee3fd7148b7f73e6a224da0f04dfb88667c12d77576
+oid sha256:ecb862d90565d7dabbd67354d185b38ddef25458ed6d150cb57ef591e8ac0e88
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce58f909295a9720fe6030e07b94a50b8fc05aaa74f84197f54b31693c13f3e
+oid sha256:d5dbeaae840c06add40fff35d8c2d57372112cc4346db608c6f527351fc5626b
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16599d618a7d7919da8a82ac4d47d26049f78ab61a2cb04e65de66bc633156ee
+oid sha256:982e46569596a9098aca2aba35c809fcb0fcbcb20f18bbb2b872db950802cc3a
 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": 1.7173281908035278,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.000581192607230036,
+  "best_metric": 1.386073112487793,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001162385214460072,
   "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": 61.513,
       "eval_steps_per_second": 15.38,
       "step": 10
+    },
+    {
+      "epoch": 0.0006974311286760432,
+      "grad_norm": 2.9086358547210693,
+      "learning_rate": 0.000163742398974869,
+      "loss": 6.7148,
+      "step": 12
+    },
+    {
+      "epoch": 0.0008717889108450541,
+      "grad_norm": 3.048389196395874,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.5216,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008717889108450541,
+      "eval_loss": 1.4961720705032349,
+      "eval_runtime": 235.7834,
+      "eval_samples_per_second": 61.455,
+      "eval_steps_per_second": 15.366,
+      "step": 15
+    },
+    {
+      "epoch": 0.001046146693014065,
+      "grad_norm": 3.2019808292388916,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 6.2214,
+      "step": 18
+    },
+    {
+      "epoch": 0.001162385214460072,
+      "eval_loss": 1.386073112487793,
+      "eval_runtime": 235.5561,
+      "eval_samples_per_second": 61.514,
+      "eval_steps_per_second": 15.381,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1352272969728000.0,
+  "total_flos": 2554293387264000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null