Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0efbae863edae5ba3468d772c19b58f9b7b9e98f002b3209ee94c356a252db42
+oid sha256:cc9b4a3a0507bd48a42176710db70e63abca7ae12318c250bbdcf9df9aea84c7
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09284333f5f51c21344942adec586922f72e7780acb9b145f77b3010ac64283f
+oid sha256:9907d0bfdc52ceb7a5bae96bf4206ed5d61858124566a3cbce3c036e8ed80ca2
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f0a3db0ff9d605cd3f535a9c581a546701adf2969dc1fad8a8f2bafec063c0
+oid sha256:f3a8bc69c6dd53b491a232b40fd3a0df74d8a4eeef8cc7aedf11d65012e22031
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2521739130434781,
+  "epoch": 1.4086956521739131,
   "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": 36.201,
       "eval_steps_per_second": 4.852,
       "step": 72
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 0.47509416937828064,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 1.2668,
+      "step": 75
+    },
+    {
+      "epoch": 1.3565217391304347,
+      "grad_norm": 0.36375659704208374,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 1.3312,
+      "step": 78
+    },
+    {
+      "epoch": 1.4086956521739131,
+      "grad_norm": 0.5056440830230713,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 1.2621,
+      "step": 81
+    },
+    {
+      "epoch": 1.4086956521739131,
+      "eval_loss": 0.9655399918556213,
+      "eval_runtime": 2.671,
+      "eval_samples_per_second": 36.316,
+      "eval_steps_per_second": 4.867,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8932733953703936e+16,
+  "total_flos": 2.128401785998541e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null