Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:950677b13c6b5ac1c0118a8d2490f57fb03ef28803078facb5279134c015ee30
+oid sha256:9ea328785589cc323ec1702cfb03081dc78a2e2494c0e1701952eae917cf005c
 size 231448

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa68b895c041d52af0cd5c7e2b8cc611d7d0a8b771348fd49a04034678469526
+oid sha256:90deee70f77ca2bc2a9eaca20396985913f3b282b74be00d1a8d2f35b33ebe30
 size 254640

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45491ad9eb071e7ae61f22667f2801b64828ca7c259739c1b6cdc1249a016367
+oid sha256:ee7a1bd05405050c3e41dd82cea709212be93ca28aa743ce669cae43b9229428
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd9465ef056e04d3fe99197d208af63980ee5111d270db49fe259e43c05f827d
+oid sha256:f909eae7da558935f88a00ce26b4da28103d4b055b9a1258f5dcd1e98716dcb2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.293695449829102,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.11158638646085177,
+  "best_metric": 10.29357624053955,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.1301841175376604,
   "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": 397.375,
       "eval_steps_per_second": 99.344,
       "step": 300
+    },
+    {
+      "epoch": 0.1153059326762135,
+      "grad_norm": 0.3179763853549957,
+      "learning_rate": 8.111435717083556e-05,
+      "loss": 10.3224,
+      "step": 310
+    },
+    {
+      "epoch": 0.11902547889157523,
+      "grad_norm": 0.267368882894516,
+      "learning_rate": 7.393518160188063e-05,
+      "loss": 10.3012,
+      "step": 320
+    },
+    {
+      "epoch": 0.12274502510693695,
+      "grad_norm": 0.29172074794769287,
+      "learning_rate": 6.69170945044974e-05,
+      "loss": 10.3031,
+      "step": 330
+    },
+    {
+      "epoch": 0.12646457132229869,
+      "grad_norm": 0.3083609640598297,
+      "learning_rate": 6.009428729356871e-05,
+      "loss": 10.2856,
+      "step": 340
+    },
+    {
+      "epoch": 0.1301841175376604,
+      "grad_norm": 0.47518908977508545,
+      "learning_rate": 5.3500000000000026e-05,
+      "loss": 10.2669,
+      "step": 350
+    },
+    {
+      "epoch": 0.1301841175376604,
+      "eval_loss": 10.29357624053955,
+      "eval_runtime": 2.7811,
+      "eval_samples_per_second": 407.028,
+      "eval_steps_per_second": 101.757,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8139807129600.0,
+  "total_flos": 9496441651200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null