Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4a227c79a756f4041b4193fe029400c768e4fb220bda1690a44a40497f15ca
+oid sha256:16e2a4bd9e27add6166c433e7728390319cb5c2a57e14f48e953db58373e3101
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fa9ea107ed355e1702a55bfaf275d662d9e18bee8ba93874900a4dc29805547
+oid sha256:32ab41f7ac445279f429de0977179a91b63737bc5ce620e80fef9b751da041a7
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858ffaf5420905109f055dc370b50c9f0db5d0f1b10c2f4496d7349612d81ec4
+oid sha256:1196200b87564fcc440e04dafa8818810b70e6b70bd8a68d5aa32697baecab70
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ea7fdc27d3a55e20051ff7c0b0952cd04b9d78f6edb951d9b6865b402accbc
+oid sha256:95dc17148d20a80420d084efd57531552658b423d2de44a1f82d74311ef7502d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.35801100730896,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.12287528158918698,
+  "epoch": 0.13652809065465218,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,28 @@
       "eval_samples_per_second": 34.986,
       "eval_steps_per_second": 8.747,
       "step": 900
+    },
+    {
+      "epoch": 0.1297016861219196,
+      "grad_norm": 180.63604736328125,
+      "learning_rate": 0.00025,
+      "loss": 9.1691,
+      "step": 950
+    },
+    {
+      "epoch": 0.13652809065465218,
+      "grad_norm": 113.0001449584961,
+      "learning_rate": 0.00025,
+      "loss": 9.0877,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13652809065465218,
+      "eval_loss": 2.445781707763672,
+      "eval_runtime": 176.6879,
+      "eval_samples_per_second": 34.909,
+      "eval_steps_per_second": 8.727,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -227,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.182637002784768e+17,
+  "total_flos": 3.53626333642752e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null