Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12298d24c824fe6308bd678db2810b8314804b9eaae5f915b6a4b5f6d252e270
+oid sha256:7293b0e7a1b92766120d83508be0790b1ce935904d1848297dfe3f1b0807e0c9
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de3015d854eea9a7229a97867fb01582f944798bfaa51cde9b8f3456d307302
+oid sha256:864a9085c8c7761bd46165ddb75002bdcfa7243d06d382dce05df7a294186a8d
 size 261311226

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d178086cc08e693c5bdb1856f654e3c7c62c76bc6ba2f0a6a59d8327d53089dd
+oid sha256:8018586b93f9a82c204e8047708163b66686995bc6e8f721c205b9b44deb21f1
 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": 1.8285950422286987,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00033051568710079903,
+  "best_metric": 1.7066669464111328,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0006610313742015981,
   "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": 22.117,
       "eval_steps_per_second": 5.529,
       "step": 10
+    },
+    {
+      "epoch": 0.00039661882452095884,
+      "grad_norm": 5.490819931030273,
+      "learning_rate": 0.000163742398974869,
+      "loss": 6.6181,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004957735306511986,
+      "grad_norm": 4.252570629119873,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.4918,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004957735306511986,
+      "eval_loss": 1.7456713914871216,
+      "eval_runtime": 1154.2577,
+      "eval_samples_per_second": 22.074,
+      "eval_steps_per_second": 5.519,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005949282367814382,
+      "grad_norm": 4.3551926612854,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 6.4851,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006610313742015981,
+      "eval_loss": 1.7066669464111328,
+      "eval_runtime": 1150.9346,
+      "eval_samples_per_second": 22.138,
+      "eval_steps_per_second": 5.535,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6709602671394816.0,
+  "total_flos": 1.3255556497145856e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null