Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:932129747d4bee3922c249cbd9643f946f6306931e74db9fd95f74d02fa1e4cd
+oid sha256:e325d3c36812be85e615c64aa5c90d643f566fa2e023170752c9a536860a2200
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45d7f2e2d1be5d055523b344ac6f40a6fd54dc6ac7508fc6d2835ad638e8a90
+oid sha256:2e6570816d264b02759ab94203a65b15331bca1d6c51ddae59dc642f04f11228
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134605e1e781fc705a3279e09b0cbaee66f077da601816e59f2b3169ff7952
+oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.722824811935425,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.016842105263157894,
+  "best_metric": 2.6460254192352295,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.03368421052631579,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 65.893,
       "eval_steps_per_second": 32.946,
       "step": 10
+    },
+    {
+      "epoch": 0.020210526315789474,
+      "grad_norm": 49.80840301513672,
+      "learning_rate": 0.000163742398974869,
+      "loss": 10.0518,
+      "step": 12
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 42.67620086669922,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.1562,
+      "step": 15
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "eval_loss": 2.6727020740509033,
+      "eval_runtime": 3.8096,
+      "eval_samples_per_second": 65.624,
+      "eval_steps_per_second": 32.812,
+      "step": 15
+    },
+    {
+      "epoch": 0.03031578947368421,
+      "grad_norm": 66.15996551513672,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 10.1741,
+      "step": 18
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "eval_loss": 2.6460254192352295,
+      "eval_runtime": 3.806,
+      "eval_samples_per_second": 65.686,
+      "eval_steps_per_second": 32.843,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 177003319787520.0,
+  "total_flos": 354006639575040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null