Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a814f4338a852435cceba210696f153249f301a3bb02451f544a65e3359ef15c
+oid sha256:1745abc886c6750817878d5d5a1caad2677c722fc729dabe81bd120ff8fb499f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05cce1829083e109319f71de7e19208706a846cb88ff70a6744eeb69bc54e3e
+oid sha256:253ca4d6d6df36bc74d35d479ea38b42b9b5e9395683bada01ac250a838e58b2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64edf4072e9d9de433323939eb8f5c3fbe20486acfda2f65802e2e8a8a3efd1e
+oid sha256:0d2dd23330c7a6a241dea866f3a8d0da33f690b71da00f528527985b73751b8d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1489245891571045,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.1430203914642334,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 10.666,
       "eval_steps_per_second": 1.337,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 0.9397,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.1430203914642334,
+      "eval_runtime": 178.7234,
+      "eval_samples_per_second": 10.799,
+      "eval_steps_per_second": 1.354,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.976702787313664e+16,
+  "total_flos": 6.726095314477056e+16,
   "trial_name": null,
   "trial_params": null
 }