Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4098029b7716ff739d06f8220062506fa2eabdb703b31d8d1acd04e4b4ca5612
+oid sha256:b3a62e7b6af11aec7b06eb56aaeb4b4c3b4c4b3f15be4a996855a9a76711fd9b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c60003aac1798e5ad887546706ae113ae861addb5df31abdcd5c8ab16e41e2
+oid sha256:f0f8dc74684b4f8c66be9c8aeadd1b6eec22d36dcd9b0237ca654504cb2edf13
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1536289cb73d62a2875a4749c24fda72b2a21b4512f03dda34aea93e03ca09
+oid sha256:0f3323fe783519afc87d45ddad501fb1901cdb8e5b89fb94a2c86db4ff814d51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06563354603463993,
+  "epoch": 0.07383773928896992,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 4.521,
       "eval_steps_per_second": 0.565,
       "step": 72
+    },
+    {
+      "epoch": 0.06836827711941659,
+      "grad_norm": 9.749879837036133,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 3.1491,
+      "step": 75
+    },
+    {
+      "epoch": 0.07110300820419325,
+      "grad_norm": 8.8101224899292,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.7604,
+      "step": 78
+    },
+    {
+      "epoch": 0.07383773928896992,
+      "grad_norm": 10.01700210571289,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 3.1736,
+      "step": 81
+    },
+    {
+      "epoch": 0.07383773928896992,
+      "eval_loss": 0.8615151047706604,
+      "eval_runtime": 408.7768,
+      "eval_samples_per_second": 4.521,
+      "eval_steps_per_second": 0.565,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9019652939330355e+17,
+  "total_flos": 2.148060618471506e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null