Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ca7af37aa73a2ce754fb4321387f7903cf5422390968a44f25bd510f4fd463
+oid sha256:2072adb64bf4f50b48418c52096cf79779fcaaf6e8413cf8be2acc91f7095217
 size 60576160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0ab8dff3ab63e4a1635efb311da442dc371b438ea1a2e49349f70aa62728f8
+oid sha256:7a6315e6f80a70dcc3ec3fc68841684f4ce6815fbd126520b2393416bfe5b361
 size 30896058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd4231aa69ac0041a75bebdb3bf0e58964679bc60ec5990f41dc7abe2258772
+oid sha256:d232fa33de0a3f36fb8c3451d877ed11305baa6ced4ec91f5259002aadce72f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06b275438271ccceb2a71be30d8208b5cee039dd2f8805e8f89da23f2373c89
+oid sha256:0bfba9f6f71d6bf8d4b22bdc118ed4ab52735b4c3d041fc8533613a4cc45feba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 8.317304611206055,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.7662835249042146,
+  "best_metric": 8.305614471435547,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.8939974457215837,
   "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": 123.555,
       "eval_steps_per_second": 31.45,
       "step": 300
+    },
+    {
+      "epoch": 0.7918263090676884,
+      "grad_norm": 0.7110276222229004,
+      "learning_rate": 2.9352343615079657e-05,
+      "loss": 8.3509,
+      "step": 310
+    },
+    {
+      "epoch": 0.8173690932311622,
+      "grad_norm": 0.5742895007133484,
+      "learning_rate": 2.287825473049131e-05,
+      "loss": 8.2672,
+      "step": 320
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.6707843542098999,
+      "learning_rate": 1.7126147564349132e-05,
+      "loss": 8.2678,
+      "step": 330
+    },
+    {
+      "epoch": 0.8684546615581098,
+      "grad_norm": 0.69368976354599,
+      "learning_rate": 1.214452517161218e-05,
+      "loss": 8.2203,
+      "step": 340
+    },
+    {
+      "epoch": 0.8939974457215837,
+      "grad_norm": 1.245832920074463,
+      "learning_rate": 7.975393707194009e-06,
+      "loss": 8.2846,
+      "step": 350
+    },
+    {
+      "epoch": 0.8939974457215837,
+      "eval_loss": 8.305614471435547,
+      "eval_runtime": 1.3367,
+      "eval_samples_per_second": 123.435,
+      "eval_steps_per_second": 31.42,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3097030142459904.0,
+  "total_flos": 3615550202707968.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null