Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:956683e9f9d995e13129be72e08522d432a578452f5c277aefb81b9662017613
+oid sha256:c037ac8f621c4e2f79ffa11c1320817cb29f3ac086c4944aa662f2487fd20b57
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89cd898cb2f5773a1f14451c64b3ab98466c0673060423ef2742dd0d3e89a87f
+oid sha256:00b8dd59a152f759a62559a876799533a6058c1b3a371b8adc62845c2fae8fcf
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9869a7586932c827ff9999f77838db85a0c26d3be47f91a4f32bab202da0f96
+oid sha256:35dcf07fe09b44ecdeb939341e4c74d2062874130d18a98dd15ef7552d0e61e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7fb5f22874147e56941b0c2b0e6e106f9317ff78b343462a5df511f2b8d1e2
+oid sha256:6d3338a58e0bfbbf42753b4e3cd5016702f7cda5f6424a907d04dafd472f305e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.12240716814994812,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.1632208922742111,
+  "best_metric": 0.11754260957241058,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.19042437431991294,
   "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": 5.848,
       "eval_steps_per_second": 1.466,
       "step": 300
+    },
+    {
+      "epoch": 0.16866158868335146,
+      "grad_norm": 0.062041934579610825,
+      "learning_rate": 7.997724001423507e-05,
+      "loss": 0.0804,
+      "step": 310
+    },
+    {
+      "epoch": 0.17410228509249184,
+      "grad_norm": 0.2328738570213318,
+      "learning_rate": 7.289870709344306e-05,
+      "loss": 0.079,
+      "step": 320
+    },
+    {
+      "epoch": 0.1795429815016322,
+      "grad_norm": 0.1590886265039444,
+      "learning_rate": 6.597900439462128e-05,
+      "loss": 0.1257,
+      "step": 330
+    },
+    {
+      "epoch": 0.18498367791077258,
+      "grad_norm": 0.205345019698143,
+      "learning_rate": 5.9251844013752326e-05,
+      "loss": 0.1441,
+      "step": 340
+    },
+    {
+      "epoch": 0.19042437431991294,
+      "grad_norm": 0.1600612848997116,
+      "learning_rate": 5.275000000000002e-05,
+      "loss": 0.1837,
+      "step": 350
+    },
+    {
+      "epoch": 0.19042437431991294,
+      "eval_loss": 0.11754260957241058,
+      "eval_runtime": 66.1447,
+      "eval_samples_per_second": 5.851,
+      "eval_steps_per_second": 1.466,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.816693310029824e+16,
+  "total_flos": 9.426722828058624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null