Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a92c81ee72d6f4be19ae57715110ad33e86ad056a87f3794e3e880ad496dc7
+oid sha256:a073833fe27e1d30e14ff17db75651b68ad3e8a5848732a53ee25fda06078dcc
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96cbce9a2c261196cf00e628e7df8f9449dac405c5a464ba207ffc687ad6c685
+oid sha256:76b0cde71114fb1478bc1e2be364762451183f58258530575ed2e2b64cd6930c
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2fb4f7ac4aba23939631c9f9c91472fd4a574c3f2a85d4361636f72ca9b9a8
+oid sha256:1806a9fe2950d45df5ae27410a4d3695e1b86f3fbe3c69545db0325af4115a2c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02917004282903114,
+  "epoch": 0.033337191804607015,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 24.825,
       "eval_steps_per_second": 3.105,
       "step": 63
+    },
+    {
+      "epoch": 0.03055909248755643,
+      "grad_norm": 0.477867066860199,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 1.4842,
+      "step": 66
+    },
+    {
+      "epoch": 0.03194814214608172,
+      "grad_norm": 0.5209053158760071,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 1.6676,
+      "step": 69
+    },
+    {
+      "epoch": 0.033337191804607015,
+      "grad_norm": 0.5418485403060913,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 1.6806,
+      "step": 72
+    },
+    {
+      "epoch": 0.033337191804607015,
+      "eval_loss": 1.6370091438293457,
+      "eval_runtime": 146.5808,
+      "eval_samples_per_second": 24.819,
+      "eval_steps_per_second": 3.104,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.521502090834739e+16,
+  "total_flos": 4.024573818096845e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null