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:ca38a470f48b9a3eda7dc7d31dc9611e5e3c4256687c086fd038f95746814c4f
+oid sha256:28ad4f4743381dbee21215d037183c11e23b3e9cc27a404604d3378155d8bcec
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b771855df1b735aed9eb0c2907412b59c68ae217034424530593503ec720bd4
+oid sha256:bf3666ccf9fe2cf907b046c3da7e15f51a5e1fcb4c2c4b1df677205caa7efc28
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3486605cbb0dc2a33c5840ff99d168358bcb336ad8600122970833d77d8451e2
+oid sha256:ac55e2d2ceaf564eb5fd392154c87119d856598defac5660ba8d151da131eb4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5183616876602173,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.032388663967611336,
+  "best_metric": 1.2018967866897583,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.09716599190283401,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,87 @@
       "eval_samples_per_second": 35.568,
       "eval_steps_per_second": 8.892,
       "step": 10
+    },
+    {
+      "epoch": 0.038866396761133605,
+      "grad_norm": 1.614790439605713,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.4998,
+      "step": 12
+    },
+    {
+      "epoch": 0.048582995951417005,
+      "grad_norm": 0.8673895001411438,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4005,
+      "step": 15
+    },
+    {
+      "epoch": 0.048582995951417005,
+      "eval_loss": 1.308341145515442,
+      "eval_runtime": 7.1234,
+      "eval_samples_per_second": 36.5,
+      "eval_steps_per_second": 9.125,
+      "step": 15
+    },
+    {
+      "epoch": 0.058299595141700404,
+      "grad_norm": 0.9261519312858582,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.3996,
+      "step": 18
+    },
+    {
+      "epoch": 0.06477732793522267,
+      "eval_loss": 1.2375595569610596,
+      "eval_runtime": 7.2083,
+      "eval_samples_per_second": 36.07,
+      "eval_steps_per_second": 9.017,
+      "step": 20
+    },
+    {
+      "epoch": 0.0680161943319838,
+      "grad_norm": 0.745496928691864,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.2622,
+      "step": 21
+    },
+    {
+      "epoch": 0.07773279352226721,
+      "grad_norm": 0.7845839262008667,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.252,
+      "step": 24
+    },
+    {
+      "epoch": 0.08097165991902834,
+      "eval_loss": 1.2060513496398926,
+      "eval_runtime": 7.2123,
+      "eval_samples_per_second": 36.049,
+      "eval_steps_per_second": 9.012,
+      "step": 25
+    },
+    {
+      "epoch": 0.0874493927125506,
+      "grad_norm": 0.9540892839431763,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.2789,
+      "step": 27
+    },
+    {
+      "epoch": 0.09716599190283401,
+      "grad_norm": 0.8427168130874634,
+      "learning_rate": 0.0,
+      "loss": 1.2617,
+      "step": 30
+    },
+    {
+      "epoch": 0.09716599190283401,
+      "eval_loss": 1.2018967866897583,
+      "eval_runtime": 7.2958,
+      "eval_samples_per_second": 35.637,
+      "eval_steps_per_second": 8.909,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -75,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2607004665249792.0,
+  "total_flos": 6542106046758912.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null