Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c59ad0c347f3da0a76bda73b466c6601c615d7978412d40d021022c7bc4c51
+oid sha256:f2410db1bc6245059c862774bbc63218858c23b5c10ec4e1dcc2d9cdbf6446c9
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472eb6676c54eb9279f1e5d67db0f3a80617b0b6247e93fd0ed07ea97a73cd7d
+oid sha256:99bf0a07f0f20a77dcf4ee8c190bfa18ac550a7462aff69399d6e91fda61a23e
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da23b19bfe147332d7f4cda6ddcca2a07a4601e8f77254aebaa1560512e716fc
+oid sha256:401ca6335837ae95d37d6e4cae75452d53ba4ef11d33ee268e83a644bb9acdd2
 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": 1.3194067478179932,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01634988759452279,
+  "best_metric": 1.296627163887024,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.024524831391784182,
   "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": 24.125,
       "eval_steps_per_second": 12.086,
       "step": 20
+    },
+    {
+      "epoch": 0.017167381974248927,
+      "grad_norm": 0.6224148869514465,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 1.3279,
+      "step": 21
+    },
+    {
+      "epoch": 0.019619865113427344,
+      "grad_norm": 0.605733335018158,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 1.2968,
+      "step": 24
+    },
+    {
+      "epoch": 0.020437359493153485,
+      "eval_loss": 1.3003891706466675,
+      "eval_runtime": 21.694,
+      "eval_samples_per_second": 23.739,
+      "eval_steps_per_second": 11.893,
+      "step": 25
+    },
+    {
+      "epoch": 0.022072348252605765,
+      "grad_norm": 0.5556307435035706,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.3199,
+      "step": 27
+    },
+    {
+      "epoch": 0.024524831391784182,
+      "grad_norm": 0.6132944822311401,
+      "learning_rate": 0.0,
+      "loss": 1.3598,
+      "step": 30
+    },
+    {
+      "epoch": 0.024524831391784182,
+      "eval_loss": 1.296627163887024,
+      "eval_runtime": 21.933,
+      "eval_samples_per_second": 23.481,
+      "eval_steps_per_second": 11.763,
+      "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": 1040301762281472.0,
+  "total_flos": 1560452643422208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null