Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351e09af9a0f41c330686461418fe2c9d3a03fd19fe0a6815c95188ebf54c1b4
+oid sha256:4341ef0284da9f8ceef7a0202a94b5b063a97ff39fe24eaa55bc7080932d0fbf
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b625ff135fdf2fbf99a29eb1174a164a15377e965dab2b2329106faa74ddd1
+oid sha256:316b61b7682cdc87920b7b3e4a5cd30789a0c421e2204d4d91ac2664e4b229a4
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc1ebf3c5f303b289d3c8391f7fc2045a7aead623303421c627e85c712ddcca
+oid sha256:8c7fcf973d9d67e88aeda5f4365d19ff8ed934344db35cccf9ddf4b97e1c4992
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.111658811569214,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004969191015702644,
+  "best_metric": 3.0150721073150635,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009938382031405287,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 125.488,
       "eval_steps_per_second": 15.697,
       "step": 25
+    },
+    {
+      "epoch": 0.00516795865633075,
+      "grad_norm": 0.3085891604423523,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 3.1559,
+      "step": 26
+    },
+    {
+      "epoch": 0.005366726296958855,
+      "grad_norm": 0.270420640707016,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.3095,
+      "step": 27
+    },
+    {
+      "epoch": 0.005565493937586961,
+      "grad_norm": 0.29475241899490356,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.1477,
+      "step": 28
+    },
+    {
+      "epoch": 0.005764261578215067,
+      "grad_norm": 0.2710489332675934,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.1739,
+      "step": 29
+    },
+    {
+      "epoch": 0.005963029218843173,
+      "grad_norm": 0.2811340391635895,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.1178,
+      "step": 30
+    },
+    {
+      "epoch": 0.006161796859471278,
+      "grad_norm": 0.30867451429367065,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 3.262,
+      "step": 31
+    },
+    {
+      "epoch": 0.006360564500099384,
+      "grad_norm": 0.2843790054321289,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.0734,
+      "step": 32
+    },
+    {
+      "epoch": 0.00655933214072749,
+      "grad_norm": 0.3157985806465149,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.1871,
+      "step": 33
+    },
+    {
+      "epoch": 0.006758099781355596,
+      "grad_norm": 0.33626821637153625,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 3.1768,
+      "step": 34
+    },
+    {
+      "epoch": 0.006956867421983701,
+      "grad_norm": 0.30983027815818787,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.2217,
+      "step": 35
+    },
+    {
+      "epoch": 0.007155635062611807,
+      "grad_norm": 0.3242948353290558,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.3835,
+      "step": 36
+    },
+    {
+      "epoch": 0.007354402703239913,
+      "grad_norm": 0.32097023725509644,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.1603,
+      "step": 37
+    },
+    {
+      "epoch": 0.007553170343868018,
+      "grad_norm": 0.33372122049331665,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.2361,
+      "step": 38
+    },
+    {
+      "epoch": 0.007751937984496124,
+      "grad_norm": 0.35714414715766907,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.1187,
+      "step": 39
+    },
+    {
+      "epoch": 0.007950705625124229,
+      "grad_norm": 0.3673984706401825,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.0538,
+      "step": 40
+    },
+    {
+      "epoch": 0.008149473265752336,
+      "grad_norm": 0.3406428396701813,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.2562,
+      "step": 41
+    },
+    {
+      "epoch": 0.008348240906380441,
+      "grad_norm": 0.35791170597076416,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.0969,
+      "step": 42
+    },
+    {
+      "epoch": 0.008547008547008548,
+      "grad_norm": 0.35386452078819275,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.3638,
+      "step": 43
+    },
+    {
+      "epoch": 0.008745776187636653,
+      "grad_norm": 0.3821609914302826,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.3578,
+      "step": 44
+    },
+    {
+      "epoch": 0.008944543828264758,
+      "grad_norm": 0.3941643536090851,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.2511,
+      "step": 45
+    },
+    {
+      "epoch": 0.009143311468892865,
+      "grad_norm": 0.4005015790462494,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.331,
+      "step": 46
+    },
+    {
+      "epoch": 0.00934207910952097,
+      "grad_norm": 0.4698752462863922,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.1959,
+      "step": 47
+    },
+    {
+      "epoch": 0.009540846750149075,
+      "grad_norm": 0.4824623167514801,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.4106,
+      "step": 48
+    },
+    {
+      "epoch": 0.009739614390777182,
+      "grad_norm": 0.6266025304794312,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.676,
+      "step": 49
+    },
+    {
+      "epoch": 0.009938382031405287,
+      "grad_norm": 0.9746667146682739,
+      "learning_rate": 0.0,
+      "loss": 4.1162,
+      "step": 50
+    },
+    {
+      "epoch": 0.009938382031405287,
+      "eval_loss": 3.0150721073150635,
+      "eval_runtime": 67.5705,
+      "eval_samples_per_second": 125.41,
+      "eval_steps_per_second": 15.687,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 867196041953280.0,
+  "total_flos": 1725805984481280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null