Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:000da61d1797457b2c95bcb27a7b2b110d3afb6a606a87ecd4e2f320b4fad9d7
+oid sha256:09bd95f7fd364b89b2ae4f81d4c4ca5db8f8b034fadc0d7c22d6971663b16b1a
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105ac16b5d228dd7aa94d2fb6725026dc57df3bf84599096844a4c1dedfd4e77
+oid sha256:a0e006bb684433eda15f73531a2caf513d8fd48e340ad19b335d95a7347def5c
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205bd1398626770ca707f06808286a5c34cea314101953ce4ecf1df4984e8133
+oid sha256:35fc7e171edb891fb3bf2ebbb8252949f7facee3f2a2fec8c75dafd99cbd553c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c9b643e87499abdfb160399a4a6e4965274897c037cf91e4cd5d5d65b2b404
+oid sha256:fe0a47cc675a5d4ba5fe8c0d42564476e1fe842799977ab67bf2a8317adef53f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2151703834533691,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.22853411687887693,
+  "best_metric": 1.208735466003418,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.2611818478615736,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 61.446,
       "eval_steps_per_second": 15.367,
       "step": 350
+    },
+    {
+      "epoch": 0.23506366307541626,
+      "grad_norm": 0.054964158684015274,
+      "learning_rate": 7.113080526603792e-05,
+      "loss": 1.1284,
+      "step": 360
+    },
+    {
+      "epoch": 0.2415932092719556,
+      "grad_norm": 0.07777497917413712,
+      "learning_rate": 6.607611338819697e-05,
+      "loss": 1.2268,
+      "step": 370
+    },
+    {
+      "epoch": 0.24812275546849494,
+      "grad_norm": 0.1765056848526001,
+      "learning_rate": 6.111758245266794e-05,
+      "loss": 1.2698,
+      "step": 380
+    },
+    {
+      "epoch": 0.2546523016650343,
+      "grad_norm": 0.33249780535697937,
+      "learning_rate": 5.626926795411447e-05,
+      "loss": 1.2465,
+      "step": 390
+    },
+    {
+      "epoch": 0.2611818478615736,
+      "grad_norm": 0.7363329529762268,
+      "learning_rate": 5.1544912966734994e-05,
+      "loss": 1.1405,
+      "step": 400
+    },
+    {
+      "epoch": 0.2611818478615736,
+      "eval_loss": 1.208735466003418,
+      "eval_runtime": 41.7762,
+      "eval_samples_per_second": 61.734,
+      "eval_steps_per_second": 15.439,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.692182665940173e+16,
+  "total_flos": 6.5047797694464e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null