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:b263c0419ed83039a46b26b8f9d793ea2712fb7865c3f12ecd1b7f1e38fde191
+oid sha256:fed0ec7083e4b1abd152ab9fd306c42354f2ed55674a09fbe5cd37c06ef17a46
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04462b3e544232972eda8a566be5dbb0d9c037762956d0cde88f7ddc55f8c36f
+oid sha256:1eb02f6cbce62174a18b7b7ac7b53af19ed902600ecad9e79e29414318963a5a
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31e0fdb3869a241061ca27b64da9fbd0a58f71586f852b6544558cc627e89db
+oid sha256:54d202e015217cec7b2f893b2c1397811e414d5ff08c7a02993da8b5e53e8bf0
 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": 2.4166297912597656,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003464103230276262,
+  "best_metric": 2.368725299835205,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005196154845414394,
   "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": 6.822,
       "eval_steps_per_second": 3.412,
       "step": 20
+    },
+    {
+      "epoch": 0.0036373083917900753,
+      "grad_norm": 3.117248058319092,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.2366,
+      "step": 21
+    },
+    {
+      "epoch": 0.004156923876331515,
+      "grad_norm": 2.577366590499878,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.4647,
+      "step": 24
+    },
+    {
+      "epoch": 0.004330129037845328,
+      "eval_loss": 2.3770086765289307,
+      "eval_runtime": 356.25,
+      "eval_samples_per_second": 6.824,
+      "eval_steps_per_second": 3.413,
+      "step": 25
+    },
+    {
+      "epoch": 0.004676539360872954,
+      "grad_norm": 4.037468910217285,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.3905,
+      "step": 27
+    },
+    {
+      "epoch": 0.005196154845414394,
+      "grad_norm": 2.5198121070861816,
+      "learning_rate": 0.0,
+      "loss": 2.1613,
+      "step": 30
+    },
+    {
+      "epoch": 0.005196154845414394,
+      "eval_loss": 2.368725299835205,
+      "eval_runtime": 356.3348,
+      "eval_samples_per_second": 6.822,
+      "eval_steps_per_second": 3.413,
+      "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": 7668943615426560.0,
+  "total_flos": 1.150341542313984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null