Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8731a638ea004478dc1537848282858676f57760f296ae68fed8f083688844a3
+oid sha256:6fa357842fcc971785a98f39565a0d890d4d3eae327284c62838e9a2bf2f1f5b
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94167ab79bbe37147d99cd67e0e38687155143bc1099b4667b1689241f633efc
+oid sha256:d4aa970b722ce1777cb673ba0960b06e0f00df3d471799c57e822c770c88551e
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc65900b1800458289c8c21bab3eeedd0bb320c47305aa0de9c35ef282f5293
+oid sha256:1f0301aae68db5017871275fbfdb6928fd6f7537f55caa23bacf0eda6ec47376
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3a68034a6fca5f7c1565a9344e41aadbdff3752a8799ae94336c8c84c6d63d
+oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04241435562805873,
+  "epoch": 0.08482871125611746,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 400.855,
       "eval_steps_per_second": 200.428,
       "step": 13
+    },
+    {
+      "epoch": 0.04567699836867863,
+      "grad_norm": 0.8031054139137268,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 44.2919,
+      "step": 14
+    },
+    {
+      "epoch": 0.048939641109298535,
+      "grad_norm": 0.7678930163383484,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 44.3113,
+      "step": 15
+    },
+    {
+      "epoch": 0.052202283849918436,
+      "grad_norm": 0.8228908777236938,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 44.2994,
+      "step": 16
+    },
+    {
+      "epoch": 0.05546492659053834,
+      "grad_norm": 0.8377927541732788,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 44.2779,
+      "step": 17
+    },
+    {
+      "epoch": 0.05872756933115824,
+      "grad_norm": 0.8467262387275696,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 44.2685,
+      "step": 18
+    },
+    {
+      "epoch": 0.06199021207177814,
+      "grad_norm": 0.8959646821022034,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 44.2928,
+      "step": 19
+    },
+    {
+      "epoch": 0.06525285481239804,
+      "grad_norm": 0.7665279507637024,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 44.3061,
+      "step": 20
+    },
+    {
+      "epoch": 0.06851549755301795,
+      "grad_norm": 0.8404932618141174,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 44.2792,
+      "step": 21
+    },
+    {
+      "epoch": 0.07177814029363784,
+      "grad_norm": 0.7906339168548584,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 44.2955,
+      "step": 22
+    },
+    {
+      "epoch": 0.07504078303425775,
+      "grad_norm": 0.8726968169212341,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 44.2876,
+      "step": 23
+    },
+    {
+      "epoch": 0.07830342577487764,
+      "grad_norm": 0.830900251865387,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 44.2961,
+      "step": 24
+    },
+    {
+      "epoch": 0.08156606851549755,
+      "grad_norm": 0.8512407541275024,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 44.2854,
+      "step": 25
+    },
+    {
+      "epoch": 0.08482871125611746,
+      "grad_norm": 0.8591986298561096,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 44.2909,
+      "step": 26
+    },
+    {
+      "epoch": 0.08482871125611746,
+      "eval_loss": 11.072349548339844,
+      "eval_runtime": 0.3215,
+      "eval_samples_per_second": 404.336,
+      "eval_steps_per_second": 202.168,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10646323200.0,
+  "total_flos": 21852979200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null