Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da7e409316683c633c0ae53d8d67eb49145a0d2c9bfe79abcdeef58aa19562fb
+oid sha256:6262f5ad6baf7a54fa8928af0ed91eb8ce35e148432195bdb7614d369d0fc207
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:249e5cd20467754aeb0d0ee97b688c834839dd65fa0b6cf8e70e957b74737f30
+oid sha256:caa3e1f5c23e2277e11d77181c5b35af6a5748abf78b4ed2d0f84d70b8d4eaba
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e602e0905f2f4cd3eaf79c0118d57897fc5559f4a434cf3e4f71108013ea94
+oid sha256:2bd2949875db2332096831c954b2d0057ba1bf8d4b09f9a5ce64cdf0ae619b0a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1001368761062622,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.097861647605896,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.3333333333333333,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 4.13,
       "eval_steps_per_second": 0.518,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 0.949,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.097861647605896,
+      "eval_runtime": 187.1864,
+      "eval_samples_per_second": 10.311,
+      "eval_steps_per_second": 1.293,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2719281132194202e+17,
+  "total_flos": 1.413720701218898e+17,
   "trial_name": null,
   "trial_params": null
 }