Training in progress, step 540, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f144fb2ab7f709b7d8d3f5984e577db1af7231bc78d4aafc8516809175ebcc
+oid sha256:f11cf47e1767f4e8475753e1a527c3d1324f777b6639596bd567fd3f2c481a82
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8956f0efcd4a5c8b06632bd4ba4031c9852d4e2fb5f0719b9013a55355f944fa
+oid sha256:e8055f5748bbf4e267b4180ef06a4ccf9372fc5f0506052cfe6d4506bdb2631d
 size 18985850

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5660398d064aecb705ee00c8a0778aaec0bfc48803e50e93c9478794d252f4e1
-size 14244
+oid sha256:f5ca8f65c1724ccd55a9dfea59c67c8f9c99a84dcd5a5df3c2118c7f1304f95e
+size 14180

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a65726963ec6fab44708be032f1ca48129dead8141c4a31de1936cc0473b34
+oid sha256:ba75dd4de6f32a89f3eaac79810ed1043c1489694e130f2d707e6e3c7675732b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f680b2505ce9c730748c3e16ef567136db652d51e5ad473271bf16035c0b2792
+oid sha256:e7d7d4c5e4fc777af531ac466a680ec8ca618441a7eb2767f3c7ea4ae7f49501
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.4056939501779357,
+  "epoch": 3.832740213523132,
   "eval_steps": 500,
-  "global_step": 480,
+  "global_step": 540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,22 @@
       "eval_samples_per_second": 3.836,
       "eval_steps_per_second": 0.511,
       "step": 480
+    },
+    {
+      "epoch": 3.619217081850534,
+      "eval_loss": 0.5834599733352661,
+      "eval_runtime": 23.4839,
+      "eval_samples_per_second": 3.832,
+      "eval_steps_per_second": 0.511,
+      "step": 510
+    },
+    {
+      "epoch": 3.832740213523132,
+      "eval_loss": 0.5767968893051147,
+      "eval_runtime": 23.5312,
+      "eval_samples_per_second": 3.825,
+      "eval_steps_per_second": 0.51,
+      "step": 540
     }
   ],
   "logging_steps": 30,
@@ -163,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.872209810376622e+17,
+  "total_flos": 2.1073382010047693e+17,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null