Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1349c39706954f73b87ce2e0d506e00758e8b213bb17e1a6dd1aed5c3f715b64
+oid sha256:a5ddf2f84301434e699d9c2f35b9d9105c9f4f2d8b564220a9bd359c56851edc
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76e9ed812ac31db5016397a98d34a65c97abc515da8c38a3f1a9ed81553a05d4
+oid sha256:d469aaf72c006ee445cf4f9b87e5f5cc4be9a600f4e6cccf5710fa260e9f24f8
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f4cc9cdab22e1e0f660a41fa1d4cd32f78600a13210572d12e13002a5dbf56
+oid sha256:342d36d482e38fbc36cc0a28040792e6a4257d06cd930a5ace345aee66811294
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b996514a941dd419a3f7869454171b960cb51cf1b91d9b10dbdcf1b1e50a10
+oid sha256:1074437c4c638775a20a86de2e689d1a14d0ff4e4137df2ddeb45e94a776caef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.633779525756836,
-  "best_model_checkpoint": "miner_id_24/checkpoint-60",
-  "epoch": 0.01694316978468055,
+  "best_metric": 1.6125953197479248,
+  "best_model_checkpoint": "miner_id_24/checkpoint-70",
+  "epoch": 0.019767031415460642,
   "eval_steps": 10,
-  "global_step": 60,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,6 +483,84 @@
       "eval_samples_per_second": 5.597,
       "eval_steps_per_second": 5.597,
       "step": 60
+    },
+    {
+      "epoch": 0.01722555594775856,
+      "grad_norm": 1.3225600719451904,
+      "learning_rate": 0.00019470159657616215,
+      "loss": 1.7811,
+      "step": 61
+    },
+    {
+      "epoch": 0.017507942110836568,
+      "grad_norm": 1.632053017616272,
+      "learning_rate": 0.00019449372563954293,
+      "loss": 1.8656,
+      "step": 62
+    },
+    {
+      "epoch": 0.01779032827391458,
+      "grad_norm": 1.7111440896987915,
+      "learning_rate": 0.0001942819704359693,
+      "loss": 0.8098,
+      "step": 63
+    },
+    {
+      "epoch": 0.018072714436992588,
+      "grad_norm": 1.5115035772323608,
+      "learning_rate": 0.00019406633966986828,
+      "loss": 1.0582,
+      "step": 64
+    },
+    {
+      "epoch": 0.018355100600070597,
+      "grad_norm": 2.999513626098633,
+      "learning_rate": 0.00019384684220497605,
+      "loss": 2.1569,
+      "step": 65
+    },
+    {
+      "epoch": 0.018637486763148605,
+      "grad_norm": 1.0796102285385132,
+      "learning_rate": 0.00019362348706397373,
+      "loss": 1.4516,
+      "step": 66
+    },
+    {
+      "epoch": 0.018919872926226614,
+      "grad_norm": 2.9733681678771973,
+      "learning_rate": 0.00019339628342811632,
+      "loss": 1.6857,
+      "step": 67
+    },
+    {
+      "epoch": 0.019202259089304625,
+      "grad_norm": 2.086916923522949,
+      "learning_rate": 0.0001931652406368554,
+      "loss": 0.7689,
+      "step": 68
+    },
+    {
+      "epoch": 0.019484645252382634,
+      "grad_norm": 1.511246919631958,
+      "learning_rate": 0.0001929303681874552,
+      "loss": 1.5469,
+      "step": 69
+    },
+    {
+      "epoch": 0.019767031415460642,
+      "grad_norm": 2.029017925262451,
+      "learning_rate": 0.0001926916757346022,
+      "loss": 1.3705,
+      "step": 70
+    },
+    {
+      "epoch": 0.019767031415460642,
+      "eval_loss": 1.6125953197479248,
+      "eval_runtime": 133.426,
+      "eval_samples_per_second": 5.591,
+      "eval_steps_per_second": 5.591,
+      "step": 70
     }
   ],
   "logging_steps": 1,
@@ -511,7 +589,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5872821511127040.0,
+  "total_flos": 6851625096314880.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null