Uploaded checkpoint-22500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d86c87b10946be5e19fd09e6c945826193408dd0c45733f14b421ff48c3d03
+oid sha256:1728956bca0b9356ae29462b37ac34654e1484ea8ef2b11bb5247ae5eda898c8
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3c6d36565a894febe83bdaf8decd391144d8d18bb0a4d0adc45544c47e3860
+oid sha256:e40cd6ba11d9a0ceaea16d7c58dce9d059685099ee9172ed66890d5851cdfc45
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3788580bf499dcd38db18c9ad678a723e513e1df6a53a304a6b7c2bb74dc2674
-size 14180
+oid sha256:e2411394ac968a82b73f6de27417329addc7551a6595e6f8e40c25c5f9f504b1
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba0dbbe5ceaff99b526aba1b21b83c949f035061745afe93ca5ff87a34da88f
+oid sha256:767cf16b1af6a1442d6e9081070ae709d5786da93d28d3f0bf69c41bc72162ac
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.5625,
   "eval_steps": 2500,
-  "global_step": 20000,
+  "global_step": 22500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -211,6 +211,28 @@
       "eval_samples_per_second": 4.961,
       "eval_steps_per_second": 4.961,
       "step": 20000
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 6.062647342681885,
+      "learning_rate": 8.120579710144927e-06,
+      "loss": 1.3637,
+      "step": 21000
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.603002071380615,
+      "learning_rate": 7.540869565217392e-06,
+      "loss": 1.3464,
+      "step": 22000
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 1.3194873332977295,
+      "eval_runtime": 201.6454,
+      "eval_samples_per_second": 4.959,
+      "eval_steps_per_second": 4.959,
+      "step": 22500
     }
   ],
   "logging_steps": 1000,
@@ -218,7 +240,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 3.2204251987968e+17,
+  "total_flos": 3.6229783486464e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null