Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca316e3b7fb9cc71f88c5e7f9d6b50ef8602837f741059ed91d212515da9b65
+oid sha256:1169929913bb5c932000d9767b768f52232cc25b87794b8470c01fa18b6febe3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af828b9f11cf133960b996213e9ce2588f29152e3b65859a85fbc978847fb5f
+oid sha256:ec6eb1e6db84c334570c122af91c407546f0a6028677bbf77e984e91c6f2d2a0
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e3416f587b35a71d1b3778b5dfc773e3509866855d8726ac2a4de01c335195
+oid sha256:46bad0fc23adfd09dbc19f3f7be3435ddfe15414ebed26616a6aecc380fbdf3f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
+oid sha256:5b782a524e5b57eb023365370accae538ac5e68454bafa53a6dd8b2c51cead56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8793390989303589,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.12287528158918698,
+  "best_metric": 1.8650081157684326,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.13652809065465218,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 25.228,
       "eval_steps_per_second": 6.307,
       "step": 450
+    },
+    {
+      "epoch": 0.12560584340228,
+      "grad_norm": 11.999287605285645,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 7.4036,
+      "step": 460
+    },
+    {
+      "epoch": 0.12833640521537307,
+      "grad_norm": 12.017765998840332,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 7.5689,
+      "step": 470
+    },
+    {
+      "epoch": 0.1310669670284661,
+      "grad_norm": 12.495355606079102,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 7.765,
+      "step": 480
+    },
+    {
+      "epoch": 0.13379752884155915,
+      "grad_norm": 13.036554336547852,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 7.1911,
+      "step": 490
+    },
+    {
+      "epoch": 0.13652809065465218,
+      "grad_norm": 23.29970359802246,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 7.5728,
+      "step": 500
+    },
+    {
+      "epoch": 0.13652809065465218,
+      "eval_loss": 1.8650081157684326,
+      "eval_runtime": 245.1119,
+      "eval_samples_per_second": 25.164,
+      "eval_steps_per_second": 6.291,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -430,7 +473,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.164082744066048e+17,
+  "total_flos": 3.51564749340672e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null