Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4024669463897c198606d97e6d594db0d110cc0386bf2567c16a1d0c4bdbdd37
+oid sha256:310cb3c19ba8648eac2cfc5efd2edfa9eb7aef6e777d68c2791adcdb29bcfe75
 size 60576160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fd26d675fa6a6a126306338b9f4505353715b9e6c6a2cf270cbd3fef711479
+oid sha256:c0e117a815755828fbf50e88be104a33e767c27b104de7a015ba811e06e6db5b
 size 30896058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5fb513b56a15fd673084e1d38e8da5300b1258dad221652d1257fc6c613c04a
+oid sha256:f6650480ac19d065a63aa287d558a6455d718894f4c96375f8466f0bd81805e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f76a102ac755d5bd19e6f0e55ad50e49a03a307409b32eeac7fb5a2a13752ba
+oid sha256:4b5b8ae682ae9c51a247d395336eab40b1fa2d190384873d8421e390f09af11a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.839520454406738,
-  "best_model_checkpoint": "miner_id_24/checkpoint-2850",
-  "epoch": 0.934043424825891,
+  "best_metric": 4.8373589515686035,
+  "best_model_checkpoint": "miner_id_24/checkpoint-3000",
+  "epoch": 0.9832036050798852,
   "eval_steps": 150,
-  "global_step": 2850,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -566,6 +566,35 @@
       "eval_samples_per_second": 247.137,
       "eval_steps_per_second": 61.832,
       "step": 2850
+    },
+    {
+      "epoch": 0.9504301515772224,
+      "grad_norm": 8.805246353149414,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 4.9501,
+      "step": 2900
+    },
+    {
+      "epoch": 0.9668168783285539,
+      "grad_norm": 10.70975112915039,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 4.9379,
+      "step": 2950
+    },
+    {
+      "epoch": 0.9832036050798852,
+      "grad_norm": 8.567855834960938,
+      "learning_rate": 0.0,
+      "loss": 4.9035,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9832036050798852,
+      "eval_loss": 4.8373589515686035,
+      "eval_runtime": 10.38,
+      "eval_samples_per_second": 247.592,
+      "eval_steps_per_second": 61.946,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -589,12 +618,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.95906974262231e+16,
+  "total_flos": 4.168168593004954e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null