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:aa4e4838aac217e31049ab9fc2bf91bd349ddd958c7a1a014156f07b3955952c
+oid sha256:7e2241bbb2314861b3ea6538c746f6e9e4aa7800cc9cb40e9b683de3f50e450f
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7681cba1a79d2474861a594f3a87ef6ab4a4c74c1e90e3fd3e0e87ca8a2c28ce
+oid sha256:002610962d344235b4a16e6071a935af5a881bb303bf3760970a3c68802f0826
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac973c7c7823384720c185ebbda84e83119cb388eb87e4b889926e39d54587f
+oid sha256:e4f9ebefd315b6aa0431f975c131196c12b6ed3814a868d8dd6b6b3aee982673
 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": 1.2371761798858643,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.2295143604278564,
+  "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": 4.262,
       "eval_steps_per_second": 0.534,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 1.0056,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.2295143604278564,
+      "eval_runtime": 453.1971,
+      "eval_samples_per_second": 4.259,
+      "eval_steps_per_second": 0.534,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.995607206497485e+16,
+  "total_flos": 3.3290074696679424e+16,
   "trial_name": null,
   "trial_params": null
 }