Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d735c4b89414520c131ac73a795192c84d95eef0de212348b2b51afb34f9ec4d
+oid sha256:ab364c6c93d69b87a2bcb5ab23b2b2f47336dc799e5922e1f20fa34a7a8210c8
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2ff0d4bcb6ad0b53412b2963deda9c76e73a842858859bc80e648836078da4
+oid sha256:0d375ab0412c0efb384db11223526c0934d3212360852c91620bd5073d5a15f1
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a93ac6f173601e9cf9cc746893f2796266cbc5ea513d76e893442659b6b60649
+oid sha256:72ca6365dbbc2f86eaa3db35582d2708ce0b1665aa0b50d90a15b774de232618
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2377259731292725,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 1.2366259098052979,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 15.241,
       "eval_steps_per_second": 1.911,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 1.0644,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 1.2366259098052979,
+      "eval_runtime": 126.4297,
+      "eval_samples_per_second": 15.265,
+      "eval_steps_per_second": 1.914,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.090695034659226e+16,
+  "total_flos": 7.44517848768553e+16,
   "trial_name": null,
   "trial_params": null
 }