Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c609c046d334b90f2ca09bb31a513ae88f169388223e657b0e4ee6a0be8642b3
+oid sha256:b82a33ed7a688788e789d3d454ef4700ca56ef8936e03f3bf2c3067a2780c87f
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7c94230e156551fc01d34d1cbaa90df354e6ff9057a0568ebd58dd07e1002e
+oid sha256:1376fb8ed66e9174764b45f00a345809bfd0a927539f1c78adc293f22130c6da
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f369c633e7cdbde61c687a519838babc30351943278707f66364f3dc85d9c5
+oid sha256:28bd09398ec9af0456a9ee14166cd961943ffc74000ebb4c1108e377da2d32df
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
+oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0824370384216309,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 2.1333333333333333,
+  "best_metric": 1.0762122869491577,
+  "best_model_checkpoint": "./outputs/checkpoint-1700",
+  "epoch": 2.2666666666666666,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 10.279,
       "eval_steps_per_second": 1.289,
       "step": 1600
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.0002,
+      "loss": 0.9305,
+      "step": 1700
+    },
+    {
+      "epoch": 2.27,
+      "eval_loss": 1.0762122869491577,
+      "eval_runtime": 205.0639,
+      "eval_samples_per_second": 9.412,
+      "eval_steps_per_second": 1.18,
+      "step": 1700
     }
   ],
   "logging_steps": 100,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.2614230595981312e+17,
+  "total_flos": 2.403652458643538e+17,
   "trial_name": null,
   "trial_params": null
 }