Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442c854e7ae41ddfdbaac65873b562a34014858ee67aa84276b09961fcd6ffba
+oid sha256:d1304fe9ef18373c6e35c5cca48127f96f9e883abd7f71246b64b0b278c14340
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c709dcf7322fec840e15c11d494eade2a6ff1819823ba55b658778550d64e377
+oid sha256:f2ad7dea958b6a54ca92a754845ab081fd22cf1bb384cac1f0c12fa4853968ef
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ca090cbabbbc6276e5a63bdc75efd3f7872d6abdf17c774328b833b6f41dee
+oid sha256:aac973c7c7823384720c185ebbda84e83119cb388eb87e4b889926e39d54587f
 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": 1.2442457675933838,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.2393821477890015,
+  "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": 4.215,
       "eval_steps_per_second": 0.529,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 1.0199,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.2393821477890015,
+      "eval_runtime": 467.9251,
+      "eval_samples_per_second": 4.125,
+      "eval_steps_per_second": 0.517,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.661849572995891e+16,
+  "total_flos": 2.995607206497485e+16,
   "trial_name": null,
   "trial_params": null
 }