Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13eb5b5b2878dabae83e742b0a80abcc7fbf6fd1591ebd5ec1dd7aedf4340eff
+oid sha256:c9e5374ffc68869faeae4ee771be51dc6b42422a268e6a0a502ff0a8525277cb
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0cd9e63169a7693d893221d6d496c241b259ed265c4b3827680e851a49a36e6
+oid sha256:52ef53ef5d0dca1b659a9e42edbd29e501fd6b2e3e351fb934083deb75ee3211
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c912f99eba164ba548508da56ac857cacc1455d4da877841d53bc479eccc7e5
+oid sha256:3f44422a433ce81a89551cd1cc0ce2c0494dc1515a0610a53dfff333adbf8842
 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": 1.0588235294117647,
+  "epoch": 1.1911764705882353,
   "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": 6.853,
       "eval_steps_per_second": 0.894,
       "step": 72
+    },
+    {
+      "epoch": 1.1029411764705883,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.6388,
+      "step": 75
+    },
+    {
+      "epoch": 1.1470588235294117,
+      "grad_norm": NaN,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.2662,
+      "step": 78
+    },
+    {
+      "epoch": 1.1911764705882353,
+      "grad_norm": NaN,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 9.0086,
+      "step": 81
+    },
+    {
+      "epoch": 1.1911764705882353,
+      "eval_loss": NaN,
+      "eval_runtime": 16.8654,
+      "eval_samples_per_second": 6.819,
+      "eval_steps_per_second": 0.889,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0412989438951424e+17,
+  "total_flos": 2.297238907256832e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null