Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ed38f8af1b0bd44e275e7f3e9689f9ae03a001d52102ef32a5f741ac4b9cc4
+oid sha256:41013d67c2894365b1744d3213536ab9f340e0dd6210e2adb0c7f32b73160d37
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cec2e3a755641898467bffd5a0839e31f46f9f9faa38621bf2043c3f768ef436
+oid sha256:a77c813b8ebeac5d9bb131be6ba2116acd5558040a69c763b3f56d09ef6ede2c
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e277839274dcede1dc9ad7c8ffffd9d5f234fc5c992789b16d54bd3f1aa7383
+oid sha256:2c8cc9090b5cc5d4b4246c49707d356f87bdf6b8f409039134d01740469d1b72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fce8e677bb7386f80f19f2b52163f28d827949784afc431a846b58d7c09959b
+oid sha256:e4c15c93e093cba090b2f3583592294b602741c9988a1980b16636e603079f25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3858033418655396,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.11035497517013058,
+  "best_metric": 1.359244704246521,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.12874747103181902,
   "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": 17.542,
       "eval_steps_per_second": 4.397,
       "step": 300
+    },
+    {
+      "epoch": 0.11403347434246827,
+      "grad_norm": 0.7235912084579468,
+      "learning_rate": 7.618684949223341e-05,
+      "loss": 1.4786,
+      "step": 310
+    },
+    {
+      "epoch": 0.11771197351480596,
+      "grad_norm": 0.7429346442222595,
+      "learning_rate": 6.94437920653178e-05,
+      "loss": 1.4647,
+      "step": 320
+    },
+    {
+      "epoch": 0.12139047268714365,
+      "grad_norm": 0.7758382558822632,
+      "learning_rate": 6.285203736170084e-05,
+      "loss": 1.3835,
+      "step": 330
+    },
+    {
+      "epoch": 0.12506897185948132,
+      "grad_norm": 0.7685598731040955,
+      "learning_rate": 5.6443699747697714e-05,
+      "loss": 1.2376,
+      "step": 340
+    },
+    {
+      "epoch": 0.12874747103181902,
+      "grad_norm": 1.1454414129257202,
+      "learning_rate": 5.025000000000002e-05,
+      "loss": 1.2399,
+      "step": 350
+    },
+    {
+      "epoch": 0.12874747103181902,
+      "eval_loss": 1.359244704246521,
+      "eval_runtime": 65.2526,
+      "eval_samples_per_second": 17.547,
+      "eval_steps_per_second": 4.398,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.3320825700352e+16,
+  "total_flos": 6.2207629983744e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null