Training in progress, step 3100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b33d3eec283021369b55393cb287c152e4fe9ade2d47cd9f563fedc8f2ff55
+oid sha256:279352a17ba807341e217afb26a693fced5c5c19e29613658f3fe885384b9f15
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d11af7f5a5f826609b73511dd39c85415c456adf1f7f7a2e964a7f84f8f73411
+oid sha256:e50071ac450b1ec9a4dcfcc89b7b00e9ae30e9d87ad938bab50ff4303cf96655
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9eb493e8a5e1ded45f7ff787c88732b7edf2f372416a05f1233e6e453f81d56
+oid sha256:4506919beed58b19c98839e1c17c26b50151b11f50ca31c7cc7f1e5618071106
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee5232fa4eb8d1b9b87542cf20cfe22809b071cb5309d4e2a9f60e7d3ad7ddc7
+oid sha256:78ecb8491adb59de1678c7683adb025d787487869e6e77014d8400715c3801f7
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4365726709365845,
-  "best_model_checkpoint": "./outputs/checkpoint-3000",
-  "epoch": 2.185792349726776,
+  "best_metric": 1.4254179000854492,
+  "best_model_checkpoint": "./outputs/checkpoint-3100",
+  "epoch": 2.2586520947176685,
   "eval_steps": 100,
-  "global_step": 3000,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,13 +427,27 @@
       "eval_samples_per_second": 43.702,
       "eval_steps_per_second": 5.468,
       "step": 3000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0002,
+      "loss": 1.3954,
+      "step": 3100
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 1.4254179000854492,
+      "eval_runtime": 143.4268,
+      "eval_samples_per_second": 43.744,
+      "eval_steps_per_second": 5.473,
+      "step": 3100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.7864118963540787e+17,
+  "total_flos": 1.845992464012247e+17,
   "trial_name": null,
   "trial_params": null
 }