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:afcb338ca5a8f91147ceaf4332945a521061c64430fec7f23c2e359a13334ee0
+oid sha256:894266d7d4b3b4f1e83cacae0ab90b767ca162cda9b5fe22ff4ecc1af50da37a
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f335d2a9844a46f8457c66f3c4f263e5573fd5250172e43290b0fc8e108b330e
+oid sha256:28b979c50607c84caf247bc5e6acd849afe7dd17ec2bd337f5268b92c8710a6d
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58fc649394ad4b547918752829e9d1a39d54a5807fa9572636ebb507b887ae9d
+oid sha256:dbbb2129cd435d8eabe38c58eb1df490520025270bc7a8d2ca8b4b3b2eba5385
 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": 0.8039551973342896,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03375527426160337,
+  "best_metric": 0.7770600914955139,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.05063291139240506,
   "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": 8.278,
       "eval_steps_per_second": 2.074,
       "step": 20
+    },
+    {
+      "epoch": 0.035443037974683546,
+      "grad_norm": 1.2310644388198853,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 3.2389,
+      "step": 21
+    },
+    {
+      "epoch": 0.04050632911392405,
+      "grad_norm": 1.1894452571868896,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 3.1768,
+      "step": 24
+    },
+    {
+      "epoch": 0.04219409282700422,
+      "eval_loss": 0.7809616923332214,
+      "eval_runtime": 60.8667,
+      "eval_samples_per_second": 8.198,
+      "eval_steps_per_second": 2.054,
+      "step": 25
+    },
+    {
+      "epoch": 0.04556962025316456,
+      "grad_norm": 0.9813383221626282,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 3.0257,
+      "step": 27
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 1.418955683708191,
+      "learning_rate": 0.0,
+      "loss": 3.0912,
+      "step": 30
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "eval_loss": 0.7770600914955139,
+      "eval_runtime": 60.7401,
+      "eval_samples_per_second": 8.215,
+      "eval_steps_per_second": 2.058,
+      "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": 3.46531471294464e+16,
+  "total_flos": 4.82426165919744e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null