Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1805e22edb156774f496818716d3cc828d12cd8374515404765b1d12797883d2
+oid sha256:5b3022cf43ccfe9867ae8a9c64e9aabdf2a3053b1d2c825bb5e7b4eb9c9e6841
 size 313820248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1982893803656f5557854416cc3d39272f830331f06e5ec52961c66e051e366a
+oid sha256:b439c7321226e387be653d739b1aba21a49021c9995e53a9fbaa7bcfd99f291f
 size 159641284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6609edc23837611232eabd4235e1b4e24a47ca2905ec23fd5e82b4e43eb26f32
+oid sha256:906a4c00e5c9edfe3eed563f07fc580ec44c7191fc0b782afccbe0255633e073
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ba82c4660fefa9fbbf06a718c7a06114d84fa536c01a280f55e7524e533da3
+oid sha256:1123dd497c9b8910fe9a2e80a4ab323c0694a06c711a817decbfc0ad393e20a4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6769126653671265,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.009725576645648614,
+  "best_metric": 1.6310955286026,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.01134650608659005,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 32.545,
       "eval_steps_per_second": 8.136,
       "step": 300
+    },
+    {
+      "epoch": 0.010049762533836902,
+      "grad_norm": 3.541172981262207,
+      "learning_rate": 7.84610838054344e-05,
+      "loss": 1.8639,
+      "step": 310
+    },
+    {
+      "epoch": 0.01037394842202519,
+      "grad_norm": 4.0853753089904785,
+      "learning_rate": 7.151674108219295e-05,
+      "loss": 1.6957,
+      "step": 320
+    },
+    {
+      "epoch": 0.010698134310213476,
+      "grad_norm": 3.440962076187134,
+      "learning_rate": 6.472821758145309e-05,
+      "loss": 1.6691,
+      "step": 330
+    },
+    {
+      "epoch": 0.011022320198401764,
+      "grad_norm": 3.6532485485076904,
+      "learning_rate": 5.8128586307330475e-05,
+      "loss": 1.5867,
+      "step": 340
+    },
+    {
+      "epoch": 0.01134650608659005,
+      "grad_norm": 3.979214906692505,
+      "learning_rate": 5.175000000000002e-05,
+      "loss": 1.5499,
+      "step": 350
+    },
+    {
+      "epoch": 0.01134650608659005,
+      "eval_loss": 1.6310955286026,
+      "eval_runtime": 398.0556,
+      "eval_samples_per_second": 32.629,
+      "eval_steps_per_second": 8.157,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6684131953934336e+16,
+  "total_flos": 1.9469040170827776e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null