Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c527e2911669e73c4e2e6071852e2374c56fb8da57cd6ac71b7986b568b101
+oid sha256:ee8c5dc8ba9f9bbb35fc9c94f4f2967a6da1e5f73a406700288fe9315f2a9188
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3327b4e1a408af9d66687aa974c114e3838d81a63f26382e2a950d1d86ab89ca
+oid sha256:ee773e7ad8a3d18e57d03c5ad919948eb978211d6516e1f480471e59579b8604
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b43e51c818353fdc58a80e47797b9309f858b46f69d4373d744fb2a934a15b3
+oid sha256:0fb22c85dfbc20aa45d4b5c97669f2a88c9102e142b0f1bd4f0ad19181f33e67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1883720930232558,
+  "epoch": 0.20930232558139536,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 36.425,
       "eval_steps_per_second": 4.578,
       "step": 81
+    },
+    {
+      "epoch": 0.19534883720930232,
+      "grad_norm": 2.613006830215454,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 2.3515,
+      "step": 84
+    },
+    {
+      "epoch": 0.20232558139534884,
+      "grad_norm": 3.0070550441741943,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 2.6264,
+      "step": 87
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "grad_norm": 2.684951066970825,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 2.4758,
+      "step": 90
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "eval_loss": 2.527015447616577,
+      "eval_runtime": 19.8758,
+      "eval_samples_per_second": 36.426,
+      "eval_steps_per_second": 4.578,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.116155515653325e+16,
+  "total_flos": 2.351283906281472e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null