Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de8c006689157d6b42774727743eb452ad5b33fab3afef553e31513042b885e
+oid sha256:8dcd64ac1109a6ffd90c221f18474578dd42de2ebf9364a95fbd2255f234703c
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09857bad8000d0a737f3c79c5ad10ed8a77957d4b33cc2b20adeff01140f5a56
+oid sha256:76fd3d4d3289f305320f7dc528ced94a5bbb778f4c097a64503f53ac90d6cf5b
 size 111142

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d13877ed3f59aa7198c8574c3fa03073b1b0fe0c1150b102e7c126b147c06058
+oid sha256:328fe9968df7bf20cce6c816bd538e730876deaee486e22d46258667abf17afc
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6267e78b9753bf43c76319d17432b962781d32df9e944e6f3cc798be019cdac9
+oid sha256:eba43fdf56448fad0ffc4b3800ab3289204a7137e290f6a13302e4d4c52a37fd
 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": 0.4666292765002804,
+  "epoch": 0.6999439147504206,
   "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": 270.092,
       "eval_steps_per_second": 67.523,
       "step": 26
+    },
+    {
+      "epoch": 0.4845765563656758,
+      "grad_norm": 0.1923580765724182,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3676,
+      "step": 27
+    },
+    {
+      "epoch": 0.5025238362310712,
+      "grad_norm": 0.17889352142810822,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3673,
+      "step": 28
+    },
+    {
+      "epoch": 0.5204711160964667,
+      "grad_norm": 0.19549714028835297,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3691,
+      "step": 29
+    },
+    {
+      "epoch": 0.538418395961862,
+      "grad_norm": 0.1798393279314041,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3661,
+      "step": 30
+    },
+    {
+      "epoch": 0.5563656758272574,
+      "grad_norm": 0.1796010434627533,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3674,
+      "step": 31
+    },
+    {
+      "epoch": 0.5743129556926528,
+      "grad_norm": 0.1846609115600586,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.369,
+      "step": 32
+    },
+    {
+      "epoch": 0.5922602355580482,
+      "grad_norm": 0.1805039495229721,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3641,
+      "step": 33
+    },
+    {
+      "epoch": 0.6102075154234436,
+      "grad_norm": 0.18855346739292145,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3659,
+      "step": 34
+    },
+    {
+      "epoch": 0.628154795288839,
+      "grad_norm": 0.1823464184999466,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3658,
+      "step": 35
+    },
+    {
+      "epoch": 0.6461020751542345,
+      "grad_norm": 0.17769189178943634,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3716,
+      "step": 36
+    },
+    {
+      "epoch": 0.6640493550196298,
+      "grad_norm": 0.20751889050006866,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3651,
+      "step": 37
+    },
+    {
+      "epoch": 0.6819966348850253,
+      "grad_norm": 0.20685072243213654,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3657,
+      "step": 38
+    },
+    {
+      "epoch": 0.6999439147504206,
+      "grad_norm": 0.18949469923973083,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3623,
+      "step": 39
+    },
+    {
+      "epoch": 0.6999439147504206,
+      "eval_loss": 10.366268157958984,
+      "eval_runtime": 1.3904,
+      "eval_samples_per_second": 270.433,
+      "eval_steps_per_second": 67.608,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45816943214592.0,
+  "total_flos": 68882322161664.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null