Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a4d726c503b3c750727851ab61e34d2f740afb2b25a8dbf1c7cfccd1b7135e2
+oid sha256:e68de28d7bd65af07a17e58c640ec266720dc3e9f4f62ce178c38c1c1aff958e
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31403665dbe63c261232fcb23f86a34f7bf3c3df3f168ae957c7c6b9b255cf0
+oid sha256:ae6f186abc304db2729df25a07541ab547bdc00cbf4b25d96e1a39ebd3bd6d05
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ae00f6c8d465318f682b59a73196d74014e5ae67838ca91d8967f70a23aac0
+oid sha256:62ad4ace684592e178a4b88aa8a82edcbbe0ff3fe21fc4f6323cdfe3572fa2ed
 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": 0.8440332412719727,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.16597510373443983,
+  "best_metric": 0.7681506276130676,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.33195020746887965,
   "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": 34.539,
       "eval_steps_per_second": 8.804,
       "step": 10
+    },
+    {
+      "epoch": 0.1991701244813278,
+      "grad_norm": 1.1058402061462402,
+      "learning_rate": 0.000163742398974869,
+      "loss": 3.708,
+      "step": 12
+    },
+    {
+      "epoch": 0.24896265560165975,
+      "grad_norm": 1.3736001253128052,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.6856,
+      "step": 15
+    },
+    {
+      "epoch": 0.24896265560165975,
+      "eval_loss": 0.8092417120933533,
+      "eval_runtime": 1.4781,
+      "eval_samples_per_second": 34.504,
+      "eval_steps_per_second": 8.795,
+      "step": 15
+    },
+    {
+      "epoch": 0.2987551867219917,
+      "grad_norm": 1.0854389667510986,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 3.0305,
+      "step": 18
+    },
+    {
+      "epoch": 0.33195020746887965,
+      "eval_loss": 0.7681506276130676,
+      "eval_runtime": 1.4779,
+      "eval_samples_per_second": 34.508,
+      "eval_steps_per_second": 8.796,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1231922348949504.0,
+  "total_flos": 2463844697899008.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null