Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adcf1be019a295830709b0447cadbcbebd30cabce308ff7114f9ed19aee608d7
+oid sha256:93e1220db04deef41f91568f272c1af454dc6f61e06bc94a4ba989feda28e453
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da77999fbad23a12b26a1bdeee4610518670b441ab8f59599dbb222572890bd
+oid sha256:61d14378f3c767e181a50e533483452d111e7a068d3293efc9ec3131c7e65096
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094210e52f7ab6005271dd83568f1e6f314005e45196b10710db6e1b54b3ad67
+oid sha256:b826697970fb037ea33b7c8bd23266efd49eb797e41a5119728b7a543f6d062b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
+oid sha256:60663a94a33586da5717f6f80de424ce9fe5b18a8c8d13d4ca09aa40f102443b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.087591171264648,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0009039343743644211,
+  "best_metric": 11.082609176635742,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0013559015615466317,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,92 @@
       "eval_samples_per_second": 52.891,
       "eval_steps_per_second": 26.449,
       "step": 20
+    },
+    {
+      "epoch": 0.0009491310930826422,
+      "grad_norm": 0.7993413209915161,
+      "learning_rate": 0.00019975141040730207,
+      "loss": 44.288,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009943278118008632,
+      "grad_norm": 0.6926490664482117,
+      "learning_rate": 0.0001997041811497882,
+      "loss": 44.3672,
+      "step": 22
+    },
+    {
+      "epoch": 0.0010395245305190844,
+      "grad_norm": 0.7373084425926208,
+      "learning_rate": 0.00019965285344390184,
+      "loss": 44.3927,
+      "step": 23
+    },
+    {
+      "epoch": 0.0010847212492373054,
+      "grad_norm": 0.6655643582344055,
+      "learning_rate": 0.00019959742939952392,
+      "loss": 44.3481,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011299179679555265,
+      "grad_norm": 0.7115928530693054,
+      "learning_rate": 0.00019953791129491983,
+      "loss": 44.3368,
+      "step": 25
+    },
+    {
+      "epoch": 0.0011299179679555265,
+      "eval_loss": 11.085227012634277,
+      "eval_runtime": 175.877,
+      "eval_samples_per_second": 52.975,
+      "eval_steps_per_second": 26.49,
+      "step": 25
+    },
+    {
+      "epoch": 0.0011751146866737475,
+      "grad_norm": 0.7096830010414124,
+      "learning_rate": 0.00019947430157664576,
+      "loss": 44.3735,
+      "step": 26
+    },
+    {
+      "epoch": 0.0012203114053919684,
+      "grad_norm": 0.6747312545776367,
+      "learning_rate": 0.00019940660285944803,
+      "loss": 44.3323,
+      "step": 27
+    },
+    {
+      "epoch": 0.0012655081241101896,
+      "grad_norm": 0.7371957302093506,
+      "learning_rate": 0.00019933481792615583,
+      "loss": 44.2951,
+      "step": 28
+    },
+    {
+      "epoch": 0.0013107048428284106,
+      "grad_norm": 0.7316697239875793,
+      "learning_rate": 0.0001992589497275665,
+      "loss": 44.3097,
+      "step": 29
+    },
+    {
+      "epoch": 0.0013559015615466317,
+      "grad_norm": 0.6886783838272095,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 44.3137,
+      "step": 30
+    },
+    {
+      "epoch": 0.0013559015615466317,
+      "eval_loss": 11.082609176635742,
+      "eval_runtime": 176.2695,
+      "eval_samples_per_second": 52.857,
+      "eval_steps_per_second": 26.431,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -215,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 210134630400.0,
+  "total_flos": 315201945600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null