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:a374315b367adc66e7d202b048566b281ef4e9098197218e9b388741b1b0e815
+oid sha256:2e49d4b0d5071f3f239a0f0f47a7f7fec053b2d7983fffc046bb672d719ba020
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed56ccdb9e2fcad3ad12fe5bb2fb82968d8a00b2dbc0bed640b17b8208c2d02
+oid sha256:d78deb08a1739f1916a2d02811596af48fc8e5161ca1a2fffbbec48cb49662e6
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecd56a166b4479cbb1fb1a2be0e209000a5c0185cdcac70ba840ad4be3373a0
+oid sha256:35e0e0c51d739d6f041d9711346fb0f20e3bf890350a93f6da3a668cc1a303d7
 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": 0.7212615013122559,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0010711225364181663,
+  "best_metric": 0.6244143843650818,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0021422450728363325,
   "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": 3.158,
       "eval_steps_per_second": 1.579,
       "step": 10
+    },
+    {
+      "epoch": 0.0012853470437017994,
+      "grad_norm": 0.34578871726989746,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.6988,
+      "step": 12
+    },
+    {
+      "epoch": 0.0016066838046272494,
+      "grad_norm": 0.3703376054763794,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6307,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016066838046272494,
+      "eval_loss": 0.6502181887626648,
+      "eval_runtime": 1246.9455,
+      "eval_samples_per_second": 3.153,
+      "eval_steps_per_second": 1.577,
+      "step": 15
+    },
+    {
+      "epoch": 0.0019280205655526992,
+      "grad_norm": 0.458924800157547,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.6273,
+      "step": 18
+    },
+    {
+      "epoch": 0.0021422450728363325,
+      "eval_loss": 0.6244143843650818,
+      "eval_runtime": 1247.5698,
+      "eval_samples_per_second": 3.151,
+      "eval_steps_per_second": 1.576,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8475499214929920.0,
+  "total_flos": 1.430240492519424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null