Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d0502367e3523a054c70ca77722edce61b284c92f95edef86664ff36b613ba
+oid sha256:7d2feaffcac690476949705f57e6c22b3331dcbf8c98295575c27221a206f4e9
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858e07b54b6e048d0f39890d1a64fee6e3939117e523e736caee1c437a16da6f
+oid sha256:c598bf914e6fc2dbe9569fb40de610a75400f9dcb385ca3b22e7f7d3bab9182d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82d5715858a6b453029f5e503f3f7b61d7408ce2719abf36d70ab6c90639243
+oid sha256:63aa9a735404dac131dfbc8da4c0d73a5c82d175792f71a6b89cddd41d8318a5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
+oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.110224485397339,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 2.0975825786590576,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 2.1129326047358834,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,13 +399,27 @@
       "eval_samples_per_second": 30.403,
       "eval_steps_per_second": 3.804,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 2.037,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 2.0975825786590576,
+      "eval_runtime": 206.0587,
+      "eval_samples_per_second": 30.448,
+      "eval_steps_per_second": 3.81,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.16793378136064e+16,
+  "total_flos": 8.458768314114048e+16,
   "trial_name": null,
   "trial_params": null
 }