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:ecb862d90565d7dabbd67354d185b38ddef25458ed6d150cb57ef591e8ac0e88
+oid sha256:421546ed9b9cd285e8bc599396e9b8ca143095323af656f820c5c9161da14179
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5dbeaae840c06add40fff35d8c2d57372112cc4346db608c6f527351fc5626b
+oid sha256:f45ba42eecb8bb5d28669d3565b634e8fb049259e12244aeaf9df958658a36a1
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982e46569596a9098aca2aba35c809fcb0fcbcb20f18bbb2b872db950802cc3a
+oid sha256:53be6c388cece342d6b9f74d3d243cd4c3a10b3aae6019253b01b034584f5c58
 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": 1.386073112487793,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001162385214460072,
+  "best_metric": 1.3398202657699585,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0017435778216901082,
   "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": 61.514,
       "eval_steps_per_second": 15.381,
       "step": 20
+    },
+    {
+      "epoch": 0.0012205044751830757,
+      "grad_norm": 2.8324685096740723,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.3543,
+      "step": 21
+    },
+    {
+      "epoch": 0.0013948622573520864,
+      "grad_norm": 2.5789592266082764,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 6.0648,
+      "step": 24
+    },
+    {
+      "epoch": 0.00145298151807509,
+      "eval_loss": 1.346395492553711,
+      "eval_runtime": 235.7083,
+      "eval_samples_per_second": 61.474,
+      "eval_steps_per_second": 15.371,
+      "step": 25
+    },
+    {
+      "epoch": 0.0015692200395210972,
+      "grad_norm": 2.725504159927368,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 5.876,
+      "step": 27
+    },
+    {
+      "epoch": 0.0017435778216901082,
+      "grad_norm": 2.9919424057006836,
+      "learning_rate": 0.0,
+      "loss": 6.0495,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017435778216901082,
+      "eval_loss": 1.3398202657699585,
+      "eval_runtime": 235.2336,
+      "eval_samples_per_second": 61.598,
+      "eval_steps_per_second": 15.402,
+      "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": 2554293387264000.0,
+  "total_flos": 3756313804800000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null