Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b933bb1016da231f877fc28365ee95bcdfa12a47ad7f184656054edf95a50e8b
+oid sha256:e4017786eed4832a435d58fb08aaa993374f52053894b52d14e7f41aca3abbe1
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1506a091c79d349c0bc6a5ac3ce550ad9e84bcae3339b6219dea6118a40adf15
+oid sha256:10d82842e4bef574042190af2a13c11acda4e7438d7ab5cd116b3beb51fa2db7
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffc697f673b11d0853dbcd63f147b97a246839c9a1edfcdf7272e99d718dd69f
+oid sha256:ae513b02c711a3549991d619a99f49a980c497935b01296c4517053129a02c10
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1425969cd8e5d9456eff9b286f7f5cbcd4119e2e34178d957af8f58c73bf1eea
+oid sha256:70f9eefb79e5a651e4979588997923d1fc997984394f03e9fb61aca38c6bee05
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.3517510890960693,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.006558237145855194,
+  "best_metric": 2.7597808837890625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.013116474291710388,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 19.352,
       "eval_steps_per_second": 4.841,
       "step": 50
+    },
+    {
+      "epoch": 0.007869884575026232,
+      "grad_norm": 3.23335337638855,
+      "learning_rate": 7.855555555555556e-06,
+      "loss": 2.8308,
+      "step": 60
+    },
+    {
+      "epoch": 0.009181532004197272,
+      "grad_norm": 4.3262038230896,
+      "learning_rate": 7.294444444444444e-06,
+      "loss": 2.6882,
+      "step": 70
+    },
+    {
+      "epoch": 0.01049317943336831,
+      "grad_norm": 4.342103958129883,
+      "learning_rate": 6.733333333333333e-06,
+      "loss": 2.9334,
+      "step": 80
+    },
+    {
+      "epoch": 0.01180482686253935,
+      "grad_norm": 5.277548789978027,
+      "learning_rate": 6.172222222222223e-06,
+      "loss": 2.7713,
+      "step": 90
+    },
+    {
+      "epoch": 0.013116474291710388,
+      "grad_norm": 7.770826816558838,
+      "learning_rate": 5.611111111111111e-06,
+      "loss": 2.743,
+      "step": 100
+    },
+    {
+      "epoch": 0.013116474291710388,
+      "eval_loss": 2.7597808837890625,
+      "eval_runtime": 165.1519,
+      "eval_samples_per_second": 19.437,
+      "eval_steps_per_second": 4.862,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.67755080794112e+16,
+  "total_flos": 3.35510161588224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null