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:d1304fe9ef18373c6e35c5cca48127f96f9e883abd7f71246b64b0b278c14340
+oid sha256:dd75f7f0c621d49adbe491567287289c483b65e7b1d0f2175e9a45b56cce6cf1
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ad7dea958b6a54ca92a754845ab081fd22cf1bb384cac1f0c12fa4853968ef
+oid sha256:a6984629938fc6f9e73a00b81ad84a883f39c33f4dcfc7436bd5d3d0f8a58e63
 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": 1.2393821477890015,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.232779622077942,
+  "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": 4.125,
       "eval_steps_per_second": 0.517,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 1.0077,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.232779622077942,
+      "eval_runtime": 473.1709,
+      "eval_samples_per_second": 4.079,
+      "eval_steps_per_second": 0.511,
+      "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
 }