Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab364c6c93d69b87a2bcb5ab23b2b2f47336dc799e5922e1f20fa34a7a8210c8
+oid sha256:5a42b3907e7f8aea7846f4b49be6d2858b839b3d23dcafb49a738a9518f21039
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d375ab0412c0efb384db11223526c0934d3212360852c91620bd5073d5a15f1
+oid sha256:c2c9ba921ceb3f2538fe002983bc2dd92c2ed87bf8800927bb857bf42aa552fb
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ca6365dbbc2f86eaa3db35582d2708ce0b1665aa0b50d90a15b774de232618
+oid sha256:9f9f6b90727f763e225653866388919108823474c7eb02d67d864e53ff7938d0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
+oid sha256:3e2a7616f99506ce2115c2b51a0c8d6af99dd5ac2b72ef98b701eba7ab661118
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2366259098052979,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 1.233094334602356,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 2.9333333333333336,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,20 @@
       "eval_samples_per_second": 15.265,
       "eval_steps_per_second": 1.914,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 1.0592,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.233094334602356,
+      "eval_runtime": 126.9974,
+      "eval_samples_per_second": 15.197,
+      "eval_steps_per_second": 1.906,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.44517848768553e+16,
+  "total_flos": 7.800080571706982e+16,
   "trial_name": null,
   "trial_params": null
 }