Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d58e6949a3d839a83a674d9e7045e8330ff3d573a89cf014a30ba75cf84ab51
+oid sha256:ebbe41e39f49c46555fc32241a2d314e754715ca4574742d83a7f0e5491a84a4
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724cc58cf8af01a2097c50fdf0041e72ccf78666b517d2687a16494e51ce1759
+oid sha256:c871f9a0585029209edb598fe450bd193f26baa26ab6d1b5652b77c8a17388e4
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446b19ae8dc93b9c61634f6f392296f919b70aa5f9632e225edafb6e85361eb2
+oid sha256:b18c08412ac1046c7267e2574028c1e7058f6c7d1c15c73c1cf167d5b788ca9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41439765e4324bfba55c134066121dc462eb56b67b27f6e7308aecd489d52c0e
+oid sha256:d4724a4322486cf07c6f137f6430836b1a2cb9ae0cd696f1604a47814630e3ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9808639287948608,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.019554802333539744,
+  "best_metric": 0.9416553974151611,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.02281393605579637,
   "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": 14.456,
       "eval_steps_per_second": 3.614,
       "step": 300
+    },
+    {
+      "epoch": 0.02020662907799107,
+      "grad_norm": 1.3622760772705078,
+      "learning_rate": 7.884012285763457e-05,
+      "loss": 0.7478,
+      "step": 310
+    },
+    {
+      "epoch": 0.020858455822442393,
+      "grad_norm": 1.826834797859192,
+      "learning_rate": 7.186223258500548e-05,
+      "loss": 0.8517,
+      "step": 320
+    },
+    {
+      "epoch": 0.021510282566893718,
+      "grad_norm": 1.2498234510421753,
+      "learning_rate": 6.504091428474514e-05,
+      "loss": 1.0577,
+      "step": 330
+    },
+    {
+      "epoch": 0.022162109311345043,
+      "grad_norm": 2.1019372940063477,
+      "learning_rate": 5.840940073393593e-05,
+      "loss": 0.8884,
+      "step": 340
+    },
+    {
+      "epoch": 0.02281393605579637,
+      "grad_norm": 2.712697744369507,
+      "learning_rate": 5.200000000000002e-05,
+      "loss": 1.0915,
+      "step": 350
+    },
+    {
+      "epoch": 0.02281393605579637,
+      "eval_loss": 0.9416553974151611,
+      "eval_runtime": 449.3829,
+      "eval_samples_per_second": 14.375,
+      "eval_steps_per_second": 3.594,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.248876759580672e+16,
+  "total_flos": 7.28057050646446e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null