Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c899c6f6d002878b7459b3227d0ab2a7974eb7fb79f656cd5289f06ed562f2
+oid sha256:123ed3073d733e547e73cf5c12ef1eab8bdc8d550f93d92d5a679475860b3046
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de802c958bd1724451876419402f64747f1bc80ebd7a1734ac4614c64348ec48
+oid sha256:2dc2d501999844081088c13d16787de2151850ea07748c492f4140910c07185e
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc962b30d4b753adf16f3d1980132916f69ba4d812876107f993b8f5ee15741
+oid sha256:94c43fb3684f58ec378c5792b819fb9c9b31537503ede8bc56fd06d29944f197
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9e02dc10b7239989ab9b4418ee704e53fad611ad6b77ad633028bb8eb5238dd
+oid sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07662835249042145,
+  "epoch": 0.1532567049808429,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 13.547,
       "eval_steps_per_second": 6.798,
       "step": 50
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 1.2544628381729126,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 5.4034,
+      "step": 60
+    },
+    {
+      "epoch": 0.10727969348659004,
+      "grad_norm": 2.334329605102539,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 5.6673,
+      "step": 70
+    },
+    {
+      "epoch": 0.12260536398467432,
+      "grad_norm": 1.8980088233947754,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 5.5726,
+      "step": 80
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 2.6246752738952637,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 5.9449,
+      "step": 90
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 1.715786337852478,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 5.48,
+      "step": 100
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "eval_loss": 1.420404076576233,
+      "eval_runtime": 20.3207,
+      "eval_samples_per_second": 13.533,
+      "eval_steps_per_second": 6.791,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.19979536924672e+16,
+  "total_flos": 4.48452492263424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null