Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b19ff62e166487493d552333e40379b928f307e4be8a85a24446af15d3bdb4
+oid sha256:a64ea5afdf2e0437c9f4514d8120d67ff33f3c647f682f483b90812b3e0422e3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4bf7d15eb2fcc3c935b5aa12fc95bc31126d87e4fecb3560e392757ad57d1c5
+oid sha256:d476e007387baa878b0b810d5a0071fe45f8b38ca1a31d59eda7e96e77af49ab
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f42eaccba20e352ac8df2bbc455387c66db5506dc77387306290187014f8ea
+oid sha256:03634c70ef84230f2730abe16b4f520f258194b73ac857c0f32fa6f8c7e3a541
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6248545050621033,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.01718213058419244,
+  "best_metric": 0.5925209522247314,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.03436426116838488,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 7.801,
       "eval_steps_per_second": 1.958,
       "step": 10
+    },
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 0.2894194722175598,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.4676,
+      "step": 12
+    },
+    {
+      "epoch": 0.02577319587628866,
+      "grad_norm": 0.28897491097450256,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5345,
+      "step": 15
+    },
+    {
+      "epoch": 0.02577319587628866,
+      "eval_loss": 0.6064522862434387,
+      "eval_runtime": 62.3155,
+      "eval_samples_per_second": 7.863,
+      "eval_steps_per_second": 1.974,
+      "step": 15
+    },
+    {
+      "epoch": 0.030927835051546393,
+      "grad_norm": 0.28419238328933716,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.5069,
+      "step": 18
+    },
+    {
+      "epoch": 0.03436426116838488,
+      "eval_loss": 0.5925209522247314,
+      "eval_runtime": 61.8126,
+      "eval_samples_per_second": 7.927,
+      "eval_steps_per_second": 1.99,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7975288298274816.0,
+  "total_flos": 1.5394161133879296e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null