Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82bd0bde1597f2851f097fcd6a29ede13a345e76ed7f838a92f739f3f4dd3578
+oid sha256:16ed38f8af1b0bd44e275e7f3e9689f9ae03a001d52102ef32a5f741ac4b9cc4
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0586b3a7f13e28e6b66076bae22e205d5497e2211112bea789e35266e3bcbcaf
-size 328468404
+oid sha256:cec2e3a755641898467bffd5a0839e31f46f9f9faa38621bf2043c3f768ef436
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7401ac442d77066992141eb9ea0b57d1e4f23fcc2f023e93ec7db7d6e814c0bf
+oid sha256:6e277839274dcede1dc9ad7c8ffffd9d5f234fc5c992789b16d54bd3f1aa7383
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6a94df7ac3a40cdfc424c44e0aa20bf2a24b7a45dca0fa2ca12977070a7cde
+oid sha256:8fce8e677bb7386f80f19f2b52163f28d827949784afc431a846b58d7c09959b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4156577587127686,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.09196247930844216,
+  "best_metric": 1.3858033418655396,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.11035497517013058,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 17.555,
       "eval_steps_per_second": 4.4,
       "step": 250
+    },
+    {
+      "epoch": 0.09564097848077985,
+      "grad_norm": 0.7598959803581238,
+      "learning_rate": 0.00011100511055839919,
+      "loss": 1.5345,
+      "step": 260
+    },
+    {
+      "epoch": 0.09931947765311752,
+      "grad_norm": 0.8524409532546997,
+      "learning_rate": 0.00010400739941860137,
+      "loss": 1.4252,
+      "step": 270
+    },
+    {
+      "epoch": 0.10299797682545521,
+      "grad_norm": 0.8304363489151001,
+      "learning_rate": 9.699260058139868e-05,
+      "loss": 1.3754,
+      "step": 280
+    },
+    {
+      "epoch": 0.1066764759977929,
+      "grad_norm": 0.8965967893600464,
+      "learning_rate": 8.999488944160085e-05,
+      "loss": 1.3527,
+      "step": 290
+    },
+    {
+      "epoch": 0.11035497517013058,
+      "grad_norm": 1.1299211978912354,
+      "learning_rate": 8.30483581444735e-05,
+      "loss": 1.2001,
+      "step": 300
+    },
+    {
+      "epoch": 0.11035497517013058,
+      "eval_loss": 1.3858033418655396,
+      "eval_runtime": 65.2702,
+      "eval_samples_per_second": 17.542,
+      "eval_steps_per_second": 4.397,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.443402141696e+16,
+  "total_flos": 5.3320825700352e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null