Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19984b0d8590785bfdac6e2aa6e6bf8c63fbb109b1a021b8dd66241e71b9e8b1
+oid sha256:eca7e2fdf90ebf01151fcdaeefecd9e3b95638f55ef175395818557f4d221050
 size 997533656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4335d3decd77bea658cb976fbb4bdd6da73a916d99568e5bb13fcc19ddcaef7b
+oid sha256:7ad68a7f47d5b55be9c4290c486c1477f4e7e66300877f932effff106b4c479e
 size 507180180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872dc95d9082ae8a82e28062da54d94aea6f32709064c360096e535472369f9e
+oid sha256:ed23f6cdca9482157422e04e9f6b48583551ef2cb3fcf78cf84cf5b705a87418
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
+oid sha256:c41568ec8d15c28a2145796b65c5977bed142a18699c02f8db4b41d7a5440c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5262999534606934,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.05517748758506529,
+  "best_metric": 1.4965966939926147,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.07356998344675372,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 10.677,
       "eval_steps_per_second": 2.676,
       "step": 150
+    },
+    {
+      "epoch": 0.05885598675740298,
+      "grad_norm": 0.6810901165008545,
+      "learning_rate": 0.00018740803823691298,
+      "loss": 1.5936,
+      "step": 160
+    },
+    {
+      "epoch": 0.06253448592974066,
+      "grad_norm": 0.657184362411499,
+      "learning_rate": 0.00018193523609311556,
+      "loss": 1.5681,
+      "step": 170
+    },
+    {
+      "epoch": 0.06621298510207835,
+      "grad_norm": 0.6586466431617737,
+      "learning_rate": 0.00017610710081049675,
+      "loss": 1.4321,
+      "step": 180
+    },
+    {
+      "epoch": 0.06989148427441604,
+      "grad_norm": 0.7010196447372437,
+      "learning_rate": 0.00016995202647831142,
+      "loss": 1.3784,
+      "step": 190
+    },
+    {
+      "epoch": 0.07356998344675372,
+      "grad_norm": 0.8979406356811523,
+      "learning_rate": 0.00016350000000000002,
+      "loss": 1.341,
+      "step": 200
+    },
+    {
+      "epoch": 0.07356998344675372,
+      "eval_loss": 1.4965966939926147,
+      "eval_runtime": 107.3593,
+      "eval_samples_per_second": 10.665,
+      "eval_steps_per_second": 2.673,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.0275446423552e+16,
+  "total_flos": 6.7033928564736e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null