Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e6026de3b84ceba28811a32cfbb9c3b69e390810167aff159af4add247f487c
+oid sha256:1f8dea4d325a4635d3c239e793bad657771e2130c83b3dfef9813d57f5058df9
 size 69782384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37333b1dd04e29ac205c0f9bfcc393e3b6032d9a61718e76260190d1ce080b47
+oid sha256:a691a2dd0083ffd45de8f8ba46f1319a1176b01199ed67ae21c5b8f4c7c5d65a
 size 139790651

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f49441abb975ccb348c1229085bf97990332babf644800bec7b3f3a97b104927
+oid sha256:77af5db692d8169680b37a82ccaf2369394b341d2c152f145639fd25a259d63f
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2198c886767e72e8b6e7d6fefea2fe94ace4419909b570aeb4660b8668dee2
+oid sha256:14206d6f39047b8dbff5f90ecc0ad71bc03ad9f0a166b1d0248ef5714395ce2a
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 200,
-  "best_metric": 2.348525047302246,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.21715526601520088,
+  "best_global_step": 400,
+  "best_metric": 2.2951860427856445,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.43431053203040176,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,42 @@
       "eval_samples_per_second": 66.25,
       "eval_steps_per_second": 2.091,
       "step": 200
+    },
+    {
+      "epoch": 0.2714440825190011,
+      "grad_norm": 0.6019847393035889,
+      "learning_rate": 0.00019735665616115814,
+      "loss": 2.3382,
+      "step": 250
+    },
+    {
+      "epoch": 0.3257328990228013,
+      "grad_norm": 0.7136948704719543,
+      "learning_rate": 0.00019587182680566505,
+      "loss": 2.3352,
+      "step": 300
+    },
+    {
+      "epoch": 0.3800217155266015,
+      "grad_norm": 0.6682165861129761,
+      "learning_rate": 0.00019406569810316855,
+      "loss": 2.3282,
+      "step": 350
+    },
+    {
+      "epoch": 0.43431053203040176,
+      "grad_norm": 0.6841819882392883,
+      "learning_rate": 0.00019194432300991294,
+      "loss": 2.3176,
+      "step": 400
+    },
+    {
+      "epoch": 0.43431053203040176,
+      "eval_loss": 2.2951860427856445,
+      "eval_runtime": 7.346,
+      "eval_samples_per_second": 81.949,
+      "eval_steps_per_second": 2.586,
+      "step": 400
     }
   ],
   "logging_steps": 50,
@@ -72,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.591561099791565e+16,
+  "total_flos": 1.1185423411367117e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null