Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18bc19d987e039051b6715b216add05278bb065e1ce12a9ce53a190f01609062
+oid sha256:97aeb4ba8c1c2af7a34b6441b4e768893974028a0e381f8a0d210f49a809551b
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef33ae9088f93f289f730e6aa693a51b3e12adec7e280c90863a7dba1e40990c
+oid sha256:99e35a52a7668b9866e57b7abf2354b5c9a7b143767fb9f824bd7cecac28214e
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec6f9a91562a77e005e273575d95540779ff46bc1e5fb6859a7fb68db2d1dc1
+oid sha256:748849416f869bac4aa7d1e521034011ebcc1dab5cb1cf23d6718fec84d62ab5
 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": 1.35789155960083,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003711952487008166,
+  "best_metric": 1.351155400276184,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005567928730512249,
   "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": 6.027,
       "eval_steps_per_second": 3.015,
       "step": 20
+    },
+    {
+      "epoch": 0.0038975501113585748,
+      "grad_norm": 0.41736310720443726,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.0301,
+      "step": 21
+    },
+    {
+      "epoch": 0.004454342984409799,
+      "grad_norm": 0.3389260768890381,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.1751,
+      "step": 24
+    },
+    {
+      "epoch": 0.0046399406087602076,
+      "eval_loss": 1.3520481586456299,
+      "eval_runtime": 376.6032,
+      "eval_samples_per_second": 6.025,
+      "eval_steps_per_second": 3.014,
+      "step": 25
+    },
+    {
+      "epoch": 0.005011135857461025,
+      "grad_norm": 0.27419382333755493,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.2334,
+      "step": 27
+    },
+    {
+      "epoch": 0.005567928730512249,
+      "grad_norm": 0.2178027182817459,
+      "learning_rate": 0.0,
+      "loss": 0.9741,
+      "step": 30
+    },
+    {
+      "epoch": 0.005567928730512249,
+      "eval_loss": 1.351155400276184,
+      "eval_runtime": 376.4603,
+      "eval_samples_per_second": 6.027,
+      "eval_steps_per_second": 3.015,
+      "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": 9961301379907584.0,
+  "total_flos": 1.4941952069861376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null