Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825ecd2a9b415c9b1862546edd0f3945a56a381c68920f130700de62462f1f2e
+oid sha256:aa87e4aaf0913c115ce89b309771c352257d3a5eb759996f5207f3346bf4e1cf
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064ecfb5d89792208a73611c0ec367e4fd173f534715a3b65af1db393e805133
+oid sha256:fba75799be91829a5a59efdb4d0086c4338be00a89cf104ff2f4d2e793466c29
 size 511971668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130b330e493d984dcf2540998fdf543192159617f46ed883e63a7374d38984b7
+oid sha256:e9904ec9f30d77b1d264749908e7eb7567942888015aa815ac76ce38d414eed0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
+oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4650544822216034,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.06238951856088177,
+  "best_metric": 0.4387960731983185,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.07278777165436207,
   "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": 6.282,
       "eval_steps_per_second": 1.574,
       "step": 300
+    },
+    {
+      "epoch": 0.06446916917957783,
+      "grad_norm": 1.3032387495040894,
+      "learning_rate": 8.263051337963623e-05,
+      "loss": 0.4818,
+      "step": 310
+    },
+    {
+      "epoch": 0.06654881979827389,
+      "grad_norm": 1.2554705142974854,
+      "learning_rate": 7.531714761313074e-05,
+      "loss": 0.469,
+      "step": 320
+    },
+    {
+      "epoch": 0.06862847041696996,
+      "grad_norm": 1.2291592359542847,
+      "learning_rate": 6.816788131766559e-05,
+      "loss": 0.4692,
+      "step": 330
+    },
+    {
+      "epoch": 0.07070812103566601,
+      "grad_norm": 0.8150742650032043,
+      "learning_rate": 6.121754499999055e-05,
+      "loss": 0.4679,
+      "step": 340
+    },
+    {
+      "epoch": 0.07278777165436207,
+      "grad_norm": 0.9758222699165344,
+      "learning_rate": 5.450000000000003e-05,
+      "loss": 0.4195,
+      "step": 350
+    },
+    {
+      "epoch": 0.07278777165436207,
+      "eval_loss": 0.4387960731983185,
+      "eval_runtime": 80.8477,
+      "eval_samples_per_second": 6.271,
+      "eval_steps_per_second": 1.571,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.027195140656333e+16,
+  "total_flos": 4.693949303016653e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null