Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fedf2ecd08952ac0212a4a2e0bd39ee531b1dbcb884ab75cb672fabcef11815
+oid sha256:d4a167f45c877bf8956fd2b32eec7011cd91e3be010f6acb3365ad3c9be9ce21
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0275c3e180b97a0d8ee574ce56060dce4b7e09297d6e3fbe04ed13972c83339f
+oid sha256:34d9ca278f3bc72aeb2e277e7999f977e608fd550ef4658d854012ee9ee45363
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb42c7f9a920e78023a624726d327478918c8cd450e76239e91cc8430bdb1c4
+oid sha256:79fc5761023d2ef8290e0ef42aaeae28a7d395e6c79f6a6a86323906540b02f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ae195d31357f5defc54b09ff712d3e8a645441befdccfede53a6dd1acdeebf
+oid sha256:bf46b31db7a35a4f33a788122727c08a6ae915948d136962f20a8e597d273f2e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5168118476867676,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.09259259259259259,
+  "epoch": 0.18518518518518517,
   "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": 9.587,
       "eval_steps_per_second": 2.397,
       "step": 50
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 10.893043518066406,
+      "learning_rate": 0.00021373935337780118,
+      "loss": 1.3228,
+      "step": 60
+    },
+    {
+      "epoch": 0.12962962962962962,
+      "grad_norm": 11.86053466796875,
+      "learning_rate": 0.00021295868335534802,
+      "loss": 0.9465,
+      "step": 70
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 245.02352905273438,
+      "learning_rate": 0.0002116617932785172,
+      "loss": 0.8149,
+      "step": 80
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 6.186165809631348,
+      "learning_rate": 0.00020985500146540012,
+      "loss": 0.4509,
+      "step": 90
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 8.681466102600098,
+      "learning_rate": 0.0002075471104240922,
+      "loss": 0.4001,
+      "step": 100
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "eval_loss": 0.7028859257698059,
+      "eval_runtime": 24.0444,
+      "eval_samples_per_second": 9.482,
+      "eval_steps_per_second": 2.371,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4041667963191296e+16,
+  "total_flos": 2.772558642413568e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null