Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ade82a272a26141ef0f2c3403b0e447dbb9b22bfae95cb1dfd3cd3e3a08dea
+oid sha256:6299c096c457b19d9812c1e685cede9c583e7f2a5f430edaf8bdc21bcfe53cd6
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b98e4118f185137fa077814cc686f50b657c3669104fbe7b75e1b529dc44f76
+oid sha256:72e94ec0b8a747d9361542961b40411170e3ed75970cb858ea641809a36c2e0c
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e8f00d059a4812d6770e1a218a616a479d7c655a5983886f903cb1c3e1a0406
+oid sha256:1252d792e41bb665fe1605a92d938aec774e3f7f662e20fc53dbfeaa1c4d6a22
 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": 3.3042805194854736,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.027777777777777776,
+  "best_metric": 3.2530300617218018,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.05555555555555555,
   "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": 172.185,
       "eval_steps_per_second": 43.046,
       "step": 10
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 5.118800640106201,
+      "learning_rate": 0.000163742398974869,
+      "loss": 13.5492,
+      "step": 12
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 5.077568054199219,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 13.1588,
+      "step": 15
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "eval_loss": 3.2679872512817383,
+      "eval_runtime": 1.767,
+      "eval_samples_per_second": 172.04,
+      "eval_steps_per_second": 43.01,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.772042274475098,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 12.9509,
+      "step": 18
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "eval_loss": 3.2530300617218018,
+      "eval_runtime": 1.7876,
+      "eval_samples_per_second": 170.063,
+      "eval_steps_per_second": 42.516,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 86222642872320.0,
+  "total_flos": 172445285744640.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null