Uploaded checkpoint-20000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a6cdbde4f4ccad23f4f917c627b157da08e6dc847e2ed92ac14c89589880841
+oid sha256:f8d86c87b10946be5e19fd09e6c945826193408dd0c45733f14b421ff48c3d03
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4075ec4b36d7b30f8711cdc8411eb66cf7511268abac12ba6b2db316a1ee7dd7
+oid sha256:de3c6d36565a894febe83bdaf8decd391144d8d18bb0a4d0adc45544c47e3860
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81db4d08b4f0905e940e600b34d55e9d49b371b457fe52a1dd9b0fc61bd94779
-size 14244
+oid sha256:3788580bf499dcd38db18c9ad678a723e513e1df6a53a304a6b7c2bb74dc2674
+size 14180

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a95ec91bf6b79176b87aeb9e7899423b6eea55e3aa8c4701936014715782af7e
+oid sha256:3ba0dbbe5ceaff99b526aba1b21b83c949f035061745afe93ca5ff87a34da88f
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4375,
+  "epoch": 0.5,
   "eval_steps": 2500,
-  "global_step": 17500,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,35 @@
       "eval_samples_per_second": 4.959,
       "eval_steps_per_second": 4.959,
       "step": 17500
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.8097546100616455,
+      "learning_rate": 9.85913043478261e-06,
+      "loss": 1.35,
+      "step": 18000
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 6.639487266540527,
+      "learning_rate": 9.279420289855074e-06,
+      "loss": 1.3498,
+      "step": 19000
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.806727886199951,
+      "learning_rate": 8.700289855072464e-06,
+      "loss": 1.3372,
+      "step": 20000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.3245751857757568,
+      "eval_runtime": 201.5593,
+      "eval_samples_per_second": 4.961,
+      "eval_steps_per_second": 4.961,
+      "step": 20000
     }
   ],
   "logging_steps": 1000,
@@ -189,7 +218,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 2.8178720489472e+17,
+  "total_flos": 3.2204251987968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null