Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa5fd4ebc28d2d79721c5c4a813e297c0969a568688f28e26db700235528b3d
+oid sha256:95d999a720a09a97737c26ce32c21e5de5b4236cd63a1695d94a7bc8d6c5a21a
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6de704209262516a35655290e289766d3a370f67af246d74e5f800673cdb5cf8
+oid sha256:209d76bf0744d4004c63d6a5b7dbd566ff13b3ceceead4003541fd1453451a41
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37f636af35bf52170be315b1730a36b4f8756044a4fc4662aac67b38d04372b
+oid sha256:9ce98eb3bd4988150839f3fd43c14f767dcb0ee749e6ebd7a2ba356a470c3bd7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06636885768985322,
+  "epoch": 0.09955328653477984,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 8.737,
       "eval_steps_per_second": 4.395,
       "step": 26
+    },
+    {
+      "epoch": 0.06892150606253988,
+      "grad_norm": 0.5582651495933533,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 4.7835,
+      "step": 27
+    },
+    {
+      "epoch": 0.07147415443522655,
+      "grad_norm": 0.6535090208053589,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 5.1362,
+      "step": 28
+    },
+    {
+      "epoch": 0.07402680280791321,
+      "grad_norm": 0.649197518825531,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 5.1688,
+      "step": 29
+    },
+    {
+      "epoch": 0.07657945118059988,
+      "grad_norm": 0.6213428378105164,
+      "learning_rate": 2.5e-05,
+      "loss": 4.7665,
+      "step": 30
+    },
+    {
+      "epoch": 0.07913209955328654,
+      "grad_norm": 0.5954240560531616,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 4.6579,
+      "step": 31
+    },
+    {
+      "epoch": 0.0816847479259732,
+      "grad_norm": 0.6680808067321777,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 4.7746,
+      "step": 32
+    },
+    {
+      "epoch": 0.08423739629865985,
+      "grad_norm": 0.8420075178146362,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 4.3421,
+      "step": 33
+    },
+    {
+      "epoch": 0.08679004467134652,
+      "grad_norm": 0.6272104382514954,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 5.0857,
+      "step": 34
+    },
+    {
+      "epoch": 0.08934269304403318,
+      "grad_norm": 0.6511965990066528,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 4.2033,
+      "step": 35
+    },
+    {
+      "epoch": 0.09189534141671984,
+      "grad_norm": 0.6219887733459473,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 5.0471,
+      "step": 36
+    },
+    {
+      "epoch": 0.09444798978940651,
+      "grad_norm": 0.6609371304512024,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 5.1857,
+      "step": 37
+    },
+    {
+      "epoch": 0.09700063816209317,
+      "grad_norm": 0.6283613443374634,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 4.5755,
+      "step": 38
+    },
+    {
+      "epoch": 0.09955328653477984,
+      "grad_norm": 0.6079770922660828,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 4.6142,
+      "step": 39
+    },
+    {
+      "epoch": 0.09955328653477984,
+      "eval_loss": 1.1924939155578613,
+      "eval_runtime": 18.8948,
+      "eval_samples_per_second": 8.733,
+      "eval_steps_per_second": 4.393,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.75813761171456e+16,
+  "total_flos": 2.6329597083648e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null