Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95491dcefa78a1c173090af4bbec150215e0a4f4cb0fd9008011c1fafbf8ac5e
+oid sha256:5ce22bdb1d49c68e0efc5424bfdbd884977280e695b7b367313af903c1ce1d72
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958c3064f8d14fb48b1209c1f7aadc310585ab49c676a8300c0c09a6a43d63bd
+oid sha256:1da092be2eff288e8febebf1204d0f3a28ff77146b05861f79ef77c3b6ba8603
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68bcb833fcff837272c9180bcc9f8c8026a43f603dabe8af2fb220f28a9677df
+oid sha256:1d1f086bd1035ab8cc673b7d310e7ef2d72721fe09f2bf3f4f1d40725d551247
 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": 2.3167905807495117,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.015622558975160131,
+  "best_metric": 2.3112847805023193,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.023433838462740195,
   "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": 13.811,
       "eval_steps_per_second": 3.456,
       "step": 100
+    },
+    {
+      "epoch": 0.017184814872676143,
+      "grad_norm": 0.48078733682632446,
+      "learning_rate": 5.095e-06,
+      "loss": 2.1942,
+      "step": 110
+    },
+    {
+      "epoch": 0.018747070770192158,
+      "grad_norm": 0.4038431644439697,
+      "learning_rate": 4.5288888888888885e-06,
+      "loss": 2.2842,
+      "step": 120
+    },
+    {
+      "epoch": 0.02030932666770817,
+      "grad_norm": 0.489139199256897,
+      "learning_rate": 3.9627777777777784e-06,
+      "loss": 2.314,
+      "step": 130
+    },
+    {
+      "epoch": 0.021871582565224184,
+      "grad_norm": 0.49106886982917786,
+      "learning_rate": 3.3966666666666666e-06,
+      "loss": 2.2609,
+      "step": 140
+    },
+    {
+      "epoch": 0.023433838462740195,
+      "grad_norm": 0.8030147552490234,
+      "learning_rate": 2.830555555555556e-06,
+      "loss": 2.3761,
+      "step": 150
+    },
+    {
+      "epoch": 0.023433838462740195,
+      "eval_loss": 2.3112847805023193,
+      "eval_runtime": 146.4503,
+      "eval_samples_per_second": 13.807,
+      "eval_steps_per_second": 3.455,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.489881818090701e+16,
+  "total_flos": 3.722496579521741e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null