Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18255fe5135178314b30055383eafe42aff76eadea0bb29e901c3073a21986e5
+oid sha256:f31578f2ee619d84fe263695ffc6d0ea695c3ffcda0dbd63f05764ff754541e8
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42b612e820f407c57af3d3d93f638a47035bfbce0b3266e5cd223bc96ec1673
+oid sha256:faafc0c3e735ceeddc1cfb937e1c91e7965b6bd19f0a3b7bbf43b01e005e0111
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a3a2e7f87b24b5cd339ace17128f363e2805a5c9b3761ecc5ef97cd28ba615
+oid sha256:773be59c20afd641e7916cd56aeef99133cb59b4168ce3fcef9b62cf2c047e84
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
+oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.183451771736145,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 1.1814736127853394,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 2.6666666666666665,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,20 @@
       "eval_samples_per_second": 4.262,
       "eval_steps_per_second": 0.534,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 0.9541,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.1814736127853394,
+      "eval_runtime": 456.1407,
+      "eval_samples_per_second": 4.231,
+      "eval_steps_per_second": 0.531,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.321054100743782e+16,
+  "total_flos": 6.653895699274138e+16,
   "trial_name": null,
   "trial_params": null
 }