Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6835213552c3129524831ed6ef9892b2263f0ea5d41e24298fa7e589d02885e7
+oid sha256:e618084a1f0f6a637a2fda921ab72607ed162124b2c887258c9a5e0c5e5c090f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffd4df5f63aec4d8cd6f8b5148a49788a657ec5703271379192d37b1ec96d69
+oid sha256:f8be2d29107e66c2c66f797028c63ac70a09d965a9d181a549306bd7488cd517
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4329764fc299dd85a84b7a55661e86fcab9bb1b815145a2c18430ce0fa85af0f
+oid sha256:b282f04de260040fb20ce8f68d3f23a0f5f33e104a69b7ece5f30022e97e831e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da9db9fb6671f70d2a4e7001f6523f325b24520bef80a5a7ba3fc8703a924b
+oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4337732791900635,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0015241869415283786,
+  "best_metric": 1.4148930311203003,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0022862804122925676,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 9.581,
       "eval_steps_per_second": 4.791,
       "step": 20
+    },
+    {
+      "epoch": 0.0016003962886047974,
+      "grad_norm": 1.7388322353363037,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 5.6009,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018290243298340542,
+      "grad_norm": 1.4908473491668701,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 5.7861,
+      "step": 24
+    },
+    {
+      "epoch": 0.001905233676910473,
+      "eval_loss": 1.4180728197097778,
+      "eval_runtime": 577.4041,
+      "eval_samples_per_second": 9.569,
+      "eval_steps_per_second": 4.785,
+      "step": 25
+    },
+    {
+      "epoch": 0.002057652371063311,
+      "grad_norm": 1.9322134256362915,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 5.9768,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022862804122925676,
+      "grad_norm": 1.5453134775161743,
+      "learning_rate": 0.0,
+      "loss": 5.8012,
+      "step": 30
+    },
+    {
+      "epoch": 0.0022862804122925676,
+      "eval_loss": 1.4148930311203003,
+      "eval_runtime": 578.3904,
+      "eval_samples_per_second": 9.552,
+      "eval_steps_per_second": 4.777,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null