Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09eb1706f79fb5bac311eac1293d139a4d11a741535b760743cb39883a42e60d
+oid sha256:eb9df9426431ea92a2d2b6a3bb8220df310c4e338553a2274cd555c594f0a431
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44bf197f2580a2d1a65125a846ed713de640f2d370d2c5f302eee5d073b6f9b
+oid sha256:5c7097618feeae4b10c65f2b833f4387153bc04d3c8a8940d46953d378589fea
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bafc797f42e79bef23b1c8ab39314b82d3082adc76e6aeacfbddd047c4f8ca0
+oid sha256:e61a14473e935e905ee623a56bdf5b0f90f19796221bae09c58fc8379bf80d64
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f907450757c510bc85cf5ba3c442a20b76731dbae558c5d4cdc37061b46d99
+oid sha256:9d42e03a0a3d94b2b0007a43190dd2041868878539beefabe7cf790df6d1d4f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.74811851978302,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.07698229407236336,
+  "best_metric": 1.7449040412902832,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.08553588230262595,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 16.077,
       "eval_steps_per_second": 4.023,
       "step": 450
+    },
+    {
+      "epoch": 0.07869301171841588,
+      "grad_norm": 1.057092547416687,
+      "learning_rate": 4.009414470383994e-06,
+      "loss": 1.7646,
+      "step": 460
+    },
+    {
+      "epoch": 0.0804037293644684,
+      "grad_norm": 1.4289474487304688,
+      "learning_rate": 2.261723324051111e-06,
+      "loss": 1.7274,
+      "step": 470
+    },
+    {
+      "epoch": 0.08211444701052091,
+      "grad_norm": 1.5232162475585938,
+      "learning_rate": 1.0072548852474675e-06,
+      "loss": 1.6957,
+      "step": 480
+    },
+    {
+      "epoch": 0.08382516465657343,
+      "grad_norm": 1.9836598634719849,
+      "learning_rate": 2.5212079810819554e-07,
+      "loss": 1.7129,
+      "step": 490
+    },
+    {
+      "epoch": 0.08553588230262595,
+      "grad_norm": 4.641312599182129,
+      "learning_rate": 0.0,
+      "loss": 1.7282,
+      "step": 500
+    },
+    {
+      "epoch": 0.08553588230262595,
+      "eval_loss": 1.7449040412902832,
+      "eval_runtime": 152.8074,
+      "eval_samples_per_second": 16.112,
+      "eval_steps_per_second": 4.031,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.589099188984218e+16,
+  "total_flos": 9.54134838556754e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null