Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7747fd41cab114d6a80d10f436fffa01608659cae45328704a894150a7a1ee42
+oid sha256:5524909abef78e795502572e2024aa152f285bcd7a80ffc89c7e3bc02b078043
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc282ea662d9be1d1c346d0878d1ff4484f3f04a8e34c52bcf876e3707be3cba
+oid sha256:e69e5637343508e9d45ad5a7d23abd78f38308580ecdf5b584a9e2d9f0c75766
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd3884f16f1269c0ca48b7b452b6b8d5d53d42be555761e3851bf0ccd7561f6
+oid sha256:dfaf8be53ae247332dd24016fe33ba54f82eb66ab59a691e62d323776545d891
 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": 0.38617401668653156,
+  "epoch": 0.42908224076281287,
   "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": 14.913,
       "eval_steps_per_second": 1.896,
       "step": 81
+    },
+    {
+      "epoch": 0.40047675804529204,
+      "grad_norm": 0.7010225057601929,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.3046,
+      "step": 84
+    },
+    {
+      "epoch": 0.41477949940405245,
+      "grad_norm": 0.5844500064849854,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.1629,
+      "step": 87
+    },
+    {
+      "epoch": 0.42908224076281287,
+      "grad_norm": 0.7447096109390259,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.0827,
+      "step": 90
+    },
+    {
+      "epoch": 0.42908224076281287,
+      "eval_loss": 2.2069106101989746,
+      "eval_runtime": 23.7385,
+      "eval_samples_per_second": 14.912,
+      "eval_steps_per_second": 1.896,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1206920845131776e+17,
+  "total_flos": 1.2492420589132186e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null