Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f09885decb52328def272162bad8d9acd694850c517b7f8be8ce19fb34cd05f
+oid sha256:4be155e58f8a3a8e089e08f2488f4353fbe0e72e3a603e9937ae107c0512c8cf
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef35d499dca39ab9008a5246b65c68b01f18456553122f61365427c1d107ccf8
+oid sha256:8f956427a20310e79021ac206b44bcdd0ac58f6d3decb53099670b863269523f
 size 61392180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1980b8a81f319ccadc25700dd5cd3e5d253b7e8a606170a5d816786751561299
+oid sha256:68420fccc5c7f35f9cc3d1e612d96e2553efd93b67aff435c781d5757a76c0b8
 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": 0.16372939169982945,
+  "epoch": 0.18419556566230813,
   "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": 20.61,
       "eval_steps_per_second": 2.587,
       "step": 72
+    },
+    {
+      "epoch": 0.17055144968732233,
+      "grad_norm": 0.47114595770835876,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.7471,
+      "step": 75
+    },
+    {
+      "epoch": 0.17737350767481525,
+      "grad_norm": 0.4847165644168854,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.514,
+      "step": 78
+    },
+    {
+      "epoch": 0.18419556566230813,
+      "grad_norm": 0.35954052209854126,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.9685,
+      "step": 81
+    },
+    {
+      "epoch": 0.18419556566230813,
+      "eval_loss": 1.6781070232391357,
+      "eval_runtime": 35.9632,
+      "eval_samples_per_second": 20.604,
+      "eval_steps_per_second": 2.586,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.287351909620122e+16,
+  "total_flos": 4.880136900339302e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null