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:ca504fb7c673009e3dedec6288d8cb1613bed2aaa7cbf0e33b9e91cf3f45b183
+oid sha256:ab1083db1159b2ffa4f39a5d3d6fda141d845635775bb20bb203f2f109220a92
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2e49c903c5529c79d3ff835b7da0b2d73bd7966896684017c45f52ef8574c9
+oid sha256:230e8147038da3d05c7c50b6668765f299a87bed70bd7533fbca83eaec6389df
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aef72e80bca5ad86c4740cd44eaa6a311a9485d9a446667badbb08fac831b01
+oid sha256:8a72025a75dfde9f6316cf7e78853946a2bfc45ed559fba6d15f16c4440f7ee5
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472d41c9b9333a74c9178e69008f711ff75ebcb1c9882a89e4e8e8fceffd9b44
+oid sha256:99ef6f22d42e935fbf13f0628837cd5d2513a098109335b9474dbc5e57db0c7d
 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": 0.3766410140334993,
+  "epoch": 0.564961521050249,
   "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": 11.249,
       "eval_steps_per_second": 2.83,
       "step": 26
+    },
+    {
+      "epoch": 0.3911272068809416,
+      "grad_norm": 149.88087463378906,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 21.5878,
+      "step": 27
+    },
+    {
+      "epoch": 0.4056133997283839,
+      "grad_norm": 119.75304412841797,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 21.2073,
+      "step": 28
+    },
+    {
+      "epoch": 0.4200995925758262,
+      "grad_norm": 320.1707763671875,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 17.1099,
+      "step": 29
+    },
+    {
+      "epoch": 0.4345857854232684,
+      "grad_norm": 128.20896911621094,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 16.6537,
+      "step": 30
+    },
+    {
+      "epoch": 0.4490719782707107,
+      "grad_norm": 181.88687133789062,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 19.7434,
+      "step": 31
+    },
+    {
+      "epoch": 0.463558171118153,
+      "grad_norm": 182.82069396972656,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 20.6309,
+      "step": 32
+    },
+    {
+      "epoch": 0.4780443639655953,
+      "grad_norm": 173.1058807373047,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 18.576,
+      "step": 33
+    },
+    {
+      "epoch": 0.4925305568130376,
+      "grad_norm": 266.4740295410156,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 17.5184,
+      "step": 34
+    },
+    {
+      "epoch": 0.5070167496604798,
+      "grad_norm": 405.75341796875,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 15.6519,
+      "step": 35
+    },
+    {
+      "epoch": 0.5215029425079222,
+      "grad_norm": 356.82489013671875,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 17.717,
+      "step": 36
+    },
+    {
+      "epoch": 0.5359891353553644,
+      "grad_norm": 91.6025619506836,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 17.8593,
+      "step": 37
+    },
+    {
+      "epoch": 0.5504753282028066,
+      "grad_norm": 138.64764404296875,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 15.968,
+      "step": 38
+    },
+    {
+      "epoch": 0.564961521050249,
+      "grad_norm": 87.49166107177734,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 15.2474,
+      "step": 39
+    },
+    {
+      "epoch": 0.564961521050249,
+      "eval_loss": 0.500713586807251,
+      "eval_runtime": 41.3261,
+      "eval_samples_per_second": 11.252,
+      "eval_steps_per_second": 2.831,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.85014463141249e+17,
+  "total_flos": 8.775216947118735e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null