Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb00bb1a80325e0ba08ca68b0f7f8b740e2793f0f617a5cf8ede5ebf1d6e727
+oid sha256:f306322c60c2e30d6fb8a401191379b61ad9f3755b3c57504b72276bd2d0cc5a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7398f3ed8efc1aaa5b7acf17c6384115a95eef4d9ff03eede3217162824bef3a
+oid sha256:7c5740ae5f26f65b35b3b9be75d008d7b556b57ad61107844a7cebcd75ce2af1
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaef23ad6b9358048cfa2eb81866d8f39693a1c7df686b619cd9d9ea3051d3a5
+oid sha256:b202cc35d4d82828b46ac25c2aa3b0d5b24c9fdd644bb03957f013b307cbc71d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5472972972972973,
+  "epoch": 0.6081081081081081,
   "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": 13.854,
       "eval_steps_per_second": 1.773,
       "step": 81
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 1.143998146057129,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7882,
+      "step": 84
+    },
+    {
+      "epoch": 0.5878378378378378,
+      "grad_norm": 1.0916920900344849,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.8518,
+      "step": 87
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "grad_norm": 1.289839744567871,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8249,
+      "step": 90
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "eval_loss": 1.8045200109481812,
+      "eval_runtime": 18.054,
+      "eval_samples_per_second": 13.847,
+      "eval_steps_per_second": 1.772,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2018573993679258e+17,
+  "total_flos": 1.3353971104088064e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null