Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f00cb2cdf3e00b676373a81810ca76ae743ce3b3938c9cc17637e411e8bd13
+oid sha256:62fe4eb37dcc27159b69b4272703b9ed0c60117e0bdda18be2931f03ae45a067
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42571c9a1e06628c8e694449a2b2dd952b2352962829e4ed742623ed33c92cda
+oid sha256:edc14e85a8b429accc321673e7f038fa0692a55b6909485148cd720f3388c259
 size 2013843826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0614c11755c9ed53b549df937aec9b244a409d5c59a25c18e880fe46a370049a
+oid sha256:4db48a76aa5bd653fabe778f0af4a3e86983afe7bd7ad551d58cc7012d9149c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e418e314b104fe68ea6cfc66e1fe8f22acd20504a236c8a188a9f3cb190e3e
+oid sha256:4cb0ffccf56c22a1dd3ad25cb6d79ca1624bb80d493fcdfdfc22b9a15102a512
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.041265606880188,
-  "best_model_checkpoint": "miner_id_24/checkpoint-600",
-  "epoch": 0.5085284458099375,
+  "best_metric": 1.0079442262649536,
+  "best_model_checkpoint": "miner_id_24/checkpoint-700",
+  "epoch": 0.5932831867782604,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,28 @@
       "eval_samples_per_second": 3.351,
       "eval_steps_per_second": 0.838,
       "step": 600
+    },
+    {
+      "epoch": 0.550905816294099,
+      "grad_norm": 45.71076965332031,
+      "learning_rate": 2.3671284152218764e-05,
+      "loss": 8.1111,
+      "step": 650
+    },
+    {
+      "epoch": 0.5932831867782604,
+      "grad_norm": 22.455829620361328,
+      "learning_rate": 1.0744877832587534e-05,
+      "loss": 8.1041,
+      "step": 700
+    },
+    {
+      "epoch": 0.5932831867782604,
+      "eval_loss": 1.0079442262649536,
+      "eval_runtime": 591.8525,
+      "eval_samples_per_second": 3.359,
+      "eval_steps_per_second": 0.84,
+      "step": 700
     }
   ],
   "logging_steps": 50,
@@ -175,7 +197,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5603340507283456e+18,
+  "total_flos": 2.987056392516403e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null