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:dea4b7976ba6cc61571f2332740282f3b16fd9afa7e849a976c102e1728e14a4
+oid sha256:3a3798023e81a4d74c0f4579a9025093f870a6d5f827f58cf18bad4ae4b1ab56
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dfa39e0335ccdf1182e3407ba30c3a4b25237199632d6f494ad3084d51b9690
+oid sha256:771297672f10a030791ea180ece1e5093e69f7c24fc082ff5e0358bbd9ac6174
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e795150f6ce7fa12ee4e6e03a761abfdca9e4c5647c2b5c8b15eb7fe34e24b61
+oid sha256:2687aafd47dbed4dfbd2c593fdcde924baa6858faf6466095d69b0ea0151f5a2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.792747497558594,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.016963528413910092,
+  "best_metric": 4.777852535247803,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02544529262086514,
   "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": 23.274,
       "eval_steps_per_second": 5.836,
       "step": 20
+    },
+    {
+      "epoch": 0.017811704834605598,
+      "grad_norm": 0.14668700098991394,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 4.789,
+      "step": 21
+    },
+    {
+      "epoch": 0.020356234096692113,
+      "grad_norm": 0.12921211123466492,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 4.7884,
+      "step": 24
+    },
+    {
+      "epoch": 0.021204410517387615,
+      "eval_loss": 4.779895305633545,
+      "eval_runtime": 42.6819,
+      "eval_samples_per_second": 23.265,
+      "eval_steps_per_second": 5.834,
+      "step": 25
+    },
+    {
+      "epoch": 0.022900763358778626,
+      "grad_norm": 0.12373114377260208,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 4.7802,
+      "step": 27
+    },
+    {
+      "epoch": 0.02544529262086514,
+      "grad_norm": 0.12402522563934326,
+      "learning_rate": 0.0,
+      "loss": 4.7995,
+      "step": 30
+    },
+    {
+      "epoch": 0.02544529262086514,
+      "eval_loss": 4.777852535247803,
+      "eval_runtime": 42.7043,
+      "eval_samples_per_second": 23.253,
+      "eval_steps_per_second": 5.831,
+      "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": 5220213310095360.0,
+  "total_flos": 7830319965143040.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null