Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032a2f3615ea038cad68eb4e745142365571b12fd6c44db08761dd1b577d9a9d
+oid sha256:9dc82a8ae691cc9dcae05dc67becea1b49c69c09625b6a538fd50f73ee334cc2
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc11bda63b307a87dda939d462b20a8df65fa4e20cab2aa8b8bd59bb6218354
+oid sha256:8cd9745762a163e9ede6646ead7d5dcf6d7f9fc6c7c7747e1ebdd0e384d1b341
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cb76191d564bd06bd42a9245977302b32b757c9fcc517f8fa139be549e8978
+oid sha256:9fca86cee7a7bcb48e35c1c94df5ef469e59082887b7ca37a6a90be4ec48e4d8
 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": 0.9386328458786011,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.016849199663016005,
+  "best_metric": 0.9273862242698669,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02527379949452401,
   "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": 1.516,
       "eval_steps_per_second": 0.758,
       "step": 20
+    },
+    {
+      "epoch": 0.017691659646166806,
+      "grad_norm": 2.26678466796875,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 3.862,
+      "step": 21
+    },
+    {
+      "epoch": 0.020219039595619208,
+      "grad_norm": 2.4825687408447266,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 3.3123,
+      "step": 24
+    },
+    {
+      "epoch": 0.02106149957877001,
+      "eval_loss": 0.9290638566017151,
+      "eval_runtime": 329.8404,
+      "eval_samples_per_second": 1.516,
+      "eval_steps_per_second": 0.758,
+      "step": 25
+    },
+    {
+      "epoch": 0.02274641954507161,
+      "grad_norm": 2.2778186798095703,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 3.9046,
+      "step": 27
+    },
+    {
+      "epoch": 0.02527379949452401,
+      "grad_norm": 2.4795632362365723,
+      "learning_rate": 0.0,
+      "loss": 4.1006,
+      "step": 30
+    },
+    {
+      "epoch": 0.02527379949452401,
+      "eval_loss": 0.9273862242698669,
+      "eval_runtime": 329.814,
+      "eval_samples_per_second": 1.516,
+      "eval_steps_per_second": 0.758,
+      "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": 2.0390755461758976e+16,
+  "total_flos": 3.0586133192638464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null