Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b53164836d05f641d757086fd84b35a896b3fab683ed37c0921bc168b77e68
+oid sha256:29958b50b7f6d6e302c6caffa0a81330c869c07bbc5ea975cea05fbd4bc39436
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8777f4b6293e3c86024b506390458c658174076b1804b6e8790f83808a1e420b
+oid sha256:98876f4ea44785ccb94a4f28375838455d061228e67289fc0f4d8d159118a54b
 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": 0.07265106531610199,
+  "epoch": 0.10897659797415299,
   "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": 11.125,
       "eval_steps_per_second": 2.782,
       "step": 26
+    },
+    {
+      "epoch": 0.07544533705902899,
+      "grad_norm": 19.745807647705078,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 31.4099,
+      "step": 27
+    },
+    {
+      "epoch": 0.07823960880195599,
+      "grad_norm": 20.407533645629883,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 33.3792,
+      "step": 28
+    },
+    {
+      "epoch": 0.08103388054488299,
+      "grad_norm": 18.46002197265625,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 32.646,
+      "step": 29
+    },
+    {
+      "epoch": 0.08382815228780999,
+      "grad_norm": 21.341697692871094,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 32.8125,
+      "step": 30
+    },
+    {
+      "epoch": 0.08662242403073699,
+      "grad_norm": 19.30036735534668,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 32.4647,
+      "step": 31
+    },
+    {
+      "epoch": 0.08941669577366398,
+      "grad_norm": 17.527427673339844,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 32.1851,
+      "step": 32
+    },
+    {
+      "epoch": 0.09221096751659098,
+      "grad_norm": 22.025373458862305,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 31.5842,
+      "step": 33
+    },
+    {
+      "epoch": 0.09500523925951798,
+      "grad_norm": 23.377222061157227,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 31.3084,
+      "step": 34
+    },
+    {
+      "epoch": 0.097799511002445,
+      "grad_norm": 19.32001304626465,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 34.4906,
+      "step": 35
+    },
+    {
+      "epoch": 0.10059378274537199,
+      "grad_norm": 19.37845230102539,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 33.1804,
+      "step": 36
+    },
+    {
+      "epoch": 0.10338805448829899,
+      "grad_norm": 19.92717742919922,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 34.5119,
+      "step": 37
+    },
+    {
+      "epoch": 0.10618232623122599,
+      "grad_norm": 19.28239631652832,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 34.3349,
+      "step": 38
+    },
+    {
+      "epoch": 0.10897659797415299,
+      "grad_norm": 25.358318328857422,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 34.2337,
+      "step": 39
+    },
+    {
+      "epoch": 0.10897659797415299,
+      "eval_loss": 1.0242209434509277,
+      "eval_runtime": 215.991,
+      "eval_samples_per_second": 11.163,
+      "eval_steps_per_second": 2.792,
+      "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