Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5cfedb57fb71088820f83eb16663385a55beea4ff620b3df60f4f6f4ae588f1
+oid sha256:fe6bea76585bc8dafc667508687d2d8682d061c2829ae4caf5d99fee2263e127
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5159dc853e42330371494c71a588413f008451571c7b02274ccc0ca8cd26bfb
+oid sha256:f7c81339b39a15e530e10743426f260a284d658d0fdb91f720d50e46987a8314
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c1df7250fc67b3fe51ae5bad4e4ac5dc9894ac76bb2c8c227109d7abd5a9b4
+oid sha256:1ae0f84b72620e20dcd97ba85ffc1d2aea720cc31be13dc875099edcedaa5927
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bb1aa192c7f9c0516bbbf45e738ece50573944baeb2415a4a135a1ac346045
+oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4858251810073853,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.005939300350418721,
+  "best_metric": 1.4660513401031494,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.008908950525628082,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 12.242,
       "eval_steps_per_second": 3.062,
       "step": 100
+    },
+    {
+      "epoch": 0.006533230385460592,
+      "grad_norm": 2.0615479946136475,
+      "learning_rate": 5.095e-06,
+      "loss": 1.4343,
+      "step": 110
+    },
+    {
+      "epoch": 0.007127160420502465,
+      "grad_norm": 2.4463698863983154,
+      "learning_rate": 4.5288888888888885e-06,
+      "loss": 1.4471,
+      "step": 120
+    },
+    {
+      "epoch": 0.0077210904555443365,
+      "grad_norm": 3.745335578918457,
+      "learning_rate": 3.9627777777777784e-06,
+      "loss": 1.4454,
+      "step": 130
+    },
+    {
+      "epoch": 0.008315020490586208,
+      "grad_norm": 4.0279221534729,
+      "learning_rate": 3.3966666666666666e-06,
+      "loss": 1.4979,
+      "step": 140
+    },
+    {
+      "epoch": 0.008908950525628082,
+      "grad_norm": 6.417429447174072,
+      "learning_rate": 2.830555555555556e-06,
+      "loss": 1.4139,
+      "step": 150
+    },
+    {
+      "epoch": 0.008908950525628082,
+      "eval_loss": 1.4660513401031494,
+      "eval_runtime": 433.0753,
+      "eval_samples_per_second": 12.277,
+      "eval_steps_per_second": 3.071,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9439392275759104e+16,
+  "total_flos": 4.376125878829056e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null