Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a91b74719ad68a1b5c21e5c74c443202d5ca7acf928158e09bea951890f60e
+oid sha256:5d4e2bc557a74d165ab68ce61e4c4b7fa424fc4567484dde04a362934aebec05
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a92b80f1046dd51ec05df546fd4ae4eb94c0f01945d72df0ac15b152bdc012c
+oid sha256:217e77b6063528af93b4eb710ce3ad19df6e0a73f81f51ab609b651451274561
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010430247718383311,
+  "epoch": 0.01564537157757497,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 118.833,
       "eval_steps_per_second": 59.661,
       "step": 6
+    },
+    {
+      "epoch": 0.012168622338113864,
+      "grad_norm": 0.055100347846746445,
+      "learning_rate": 0.00014,
+      "loss": 10.3785,
+      "step": 7
+    },
+    {
+      "epoch": 0.013906996957844416,
+      "grad_norm": 0.05738470330834389,
+      "learning_rate": 0.00016,
+      "loss": 10.375,
+      "step": 8
+    },
+    {
+      "epoch": 0.01564537157757497,
+      "grad_norm": 0.04711873456835747,
+      "learning_rate": 0.00018,
+      "loss": 10.3732,
+      "step": 9
+    },
+    {
+      "epoch": 0.01564537157757497,
+      "eval_loss": 10.373083114624023,
+      "eval_runtime": 2.0617,
+      "eval_samples_per_second": 117.867,
+      "eval_steps_per_second": 59.176,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 155170897920.0,
+  "total_flos": 232756346880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null