Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888d8dedc9326cf6a8610134b4289d89caf9d19ce3df5a9e4384e78ba5339bf9
+oid sha256:9d77ebb934d6d6c2762b5db2a1395583e9fad893a1f60e48bc4fe66a8dde431d
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b40b5c83e8e6227bf489187ec94e3a8645f30e9566071db957cdcce69042da
+oid sha256:9e190f27159f84f9773d7b93c5a621f87e0ed564870cfd20cd258e2c3951b263
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b117cfe96ceb3354835d5e32c778db2985d4b9cf93c68141f1a12a2457ea16a9
+oid sha256:f9532ed43e9ef2c943cdb6c187dccb9af3506203376fbf626193f69cdbe287f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.805077075958252,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0072503172013775605,
+  "best_metric": 2.800004720687866,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.010875475802066341,
   "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": 18.138,
       "eval_steps_per_second": 9.069,
       "step": 20
+    },
+    {
+      "epoch": 0.0076128330614464385,
+      "grad_norm": 0.6996583342552185,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.8924,
+      "step": 21
+    },
+    {
+      "epoch": 0.008700380641653072,
+      "grad_norm": 0.6958495378494263,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.8192,
+      "step": 24
+    },
+    {
+      "epoch": 0.00906289650172195,
+      "eval_loss": 2.8007118701934814,
+      "eval_runtime": 63.7389,
+      "eval_samples_per_second": 18.231,
+      "eval_steps_per_second": 9.115,
+      "step": 25
+    },
+    {
+      "epoch": 0.009787928221859706,
+      "grad_norm": 0.5785790681838989,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 2.8877,
+      "step": 27
+    },
+    {
+      "epoch": 0.010875475802066341,
+      "grad_norm": 0.641613781452179,
+      "learning_rate": 0.0,
+      "loss": 2.8431,
+      "step": 30
+    },
+    {
+      "epoch": 0.010875475802066341,
+      "eval_loss": 2.800004720687866,
+      "eval_runtime": 63.9413,
+      "eval_samples_per_second": 18.173,
+      "eval_steps_per_second": 9.086,
+      "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": 757002015866880.0,
+  "total_flos": 1144514952560640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null