Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443e4e4f937d73e0119310938caeeaeb381794e87ba4c05deb852213a5fa4f98
+oid sha256:9989edd6d39aaf8961b5a34753ec6791eebf90f118027c4d2afd725ea07813e3
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40a11bcf1f0c7118ef3e1efd4e6c078e8c6b74b94cd2e415a2af1297f7ed79f
+oid sha256:48d0105998f86b85fc7372df3cd1e994bb06439ed64679f8a0d6d8141ace9aa9
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb90d719e937dd8276373ed7d70fad2369f124f7cf828fbeecbc84855fde6133
+oid sha256:340592f5e69d9225e347295e4162c62abff7816a6b4972749339e4dadb7c1304
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1977bb9f4ad57391ef2df027cb00edafbd5be714333f455abd93cefc987f397c
+oid sha256:9cac6703db676f115b44e685f7aab5cd5b2de97d46fa9573dfe9f79f5e9ff058
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0061849998884915885,
+  "epoch": 0.009277499832737382,
   "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": 39.819,
       "eval_steps_per_second": 9.955,
       "step": 26
+    },
+    {
+      "epoch": 0.0064228844995874185,
+      "grad_norm": 0.5535579323768616,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0174,
+      "step": 27
+    },
+    {
+      "epoch": 0.0066607691106832494,
+      "grad_norm": 0.6739106774330139,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0377,
+      "step": 28
+    },
+    {
+      "epoch": 0.0068986537217790795,
+      "grad_norm": 0.37905821204185486,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0143,
+      "step": 29
+    },
+    {
+      "epoch": 0.0071365383328749095,
+      "grad_norm": 0.8597642779350281,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0382,
+      "step": 30
+    },
+    {
+      "epoch": 0.00737442294397074,
+      "grad_norm": 0.3920349180698395,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0144,
+      "step": 31
+    },
+    {
+      "epoch": 0.00761230755506657,
+      "grad_norm": 0.33046308159828186,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0061,
+      "step": 32
+    },
+    {
+      "epoch": 0.0078501921661624,
+      "grad_norm": 0.44863665103912354,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0412,
+      "step": 33
+    },
+    {
+      "epoch": 0.008088076777258231,
+      "grad_norm": 0.2641896605491638,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0157,
+      "step": 34
+    },
+    {
+      "epoch": 0.008325961388354062,
+      "grad_norm": 0.35212084650993347,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0171,
+      "step": 35
+    },
+    {
+      "epoch": 0.008563845999449891,
+      "grad_norm": 0.19091854989528656,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0145,
+      "step": 36
+    },
+    {
+      "epoch": 0.008801730610545722,
+      "grad_norm": 0.22365093231201172,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0156,
+      "step": 37
+    },
+    {
+      "epoch": 0.009039615221641553,
+      "grad_norm": 0.5021849274635315,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0359,
+      "step": 38
+    },
+    {
+      "epoch": 0.009277499832737382,
+      "grad_norm": 0.8826900720596313,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0497,
+      "step": 39
+    },
+    {
+      "epoch": 0.009277499832737382,
+      "eval_loss": 0.02232297882437706,
+      "eval_runtime": 711.2232,
+      "eval_samples_per_second": 39.819,
+      "eval_steps_per_second": 9.955,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.051451778773811e+16,
+  "total_flos": 1.2077177668160717e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null