Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741037faa293e3aa4a6ebc59e6eb82f8cfdfbd835422fee2eef2b885261c2068
+oid sha256:d2addf46c9d006270ac3a937f77fd51ed1699623945aa626fbdae171724bc69f
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9438c304665342120801741a06ff28dd1d8b6f58198ce62882db40c2e4589f
+oid sha256:c1f8f634ff49ca1b4ec5f2013544e270aa79ffb8a3c58592c40a95b0d6874fff
 size 511971028

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366c57510a86bf35b1e3b13316f699f46eaf375c8282646c54f791554ba45dea
+oid sha256:4199d816003f34d78151d189650e781bdcc801ba6ffb2c30d024489a5f1a698b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697eb5c311706d748c20f07b0521bb9d1f71aee638eb745112aecf80a82e51da
+oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.553749680519104,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.020796506186960592,
+  "best_metric": 0.5377894043922424,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.031194759280440885,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 6.279,
       "eval_steps_per_second": 1.573,
       "step": 100
+    },
+    {
+      "epoch": 0.02287615680565665,
+      "grad_norm": 1.927892804145813,
+      "learning_rate": 0.0002085764548830435,
+      "loss": 0.5392,
+      "step": 110
+    },
+    {
+      "epoch": 0.02495580742435271,
+      "grad_norm": 1.463425636291504,
+      "learning_rate": 0.00020524128762162305,
+      "loss": 0.5582,
+      "step": 120
+    },
+    {
+      "epoch": 0.027035458043048768,
+      "grad_norm": 1.3318297863006592,
+      "learning_rate": 0.00020143724248105043,
+      "loss": 0.549,
+      "step": 130
+    },
+    {
+      "epoch": 0.029115108661744826,
+      "grad_norm": 2.8513331413269043,
+      "learning_rate": 0.0001971828523868693,
+      "loss": 0.559,
+      "step": 140
+    },
+    {
+      "epoch": 0.031194759280440885,
+      "grad_norm": 1.3817558288574219,
+      "learning_rate": 0.0001924988442999686,
+      "loss": 0.5554,
+      "step": 150
+    },
+    {
+      "epoch": 0.031194759280440885,
+      "eval_loss": 0.5377894043922424,
+      "eval_runtime": 80.77,
+      "eval_samples_per_second": 6.277,
+      "eval_steps_per_second": 1.572,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3601784912150528e+16,
+  "total_flos": 2.026932653575373e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null