Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136f0e6a29908d39678ce631c78a5897d5dff7cb804f8194ea3fcf017453fc44
+oid sha256:e5f80f8b36d0179cd02cb663a4c378caa82207bd87d037de2446e597b9d8c98d
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f21726cdc1ca2b3b4964fba8f281d3250da7951a9c3f78f60c87c630c622e8
+oid sha256:96375a1768cdb55b7026f3b88b433c634b394fd6b8891b1ad00fd1af08fb87d6
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004899759095177821,
+  "epoch": 0.0014699277285533461,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,64 @@
       "eval_samples_per_second": 298.606,
       "eval_steps_per_second": 149.303,
       "step": 3
+    },
+    {
+      "epoch": 0.0006533012126903761,
+      "grad_norm": 0.0069983652792871,
+      "learning_rate": 8e-05,
+      "loss": 11.9312,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008166265158629701,
+      "grad_norm": 0.01158211100846529,
+      "learning_rate": 0.0001,
+      "loss": 11.9341,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009799518190355642,
+      "grad_norm": 0.0077381432056427,
+      "learning_rate": 0.00012,
+      "loss": 11.9312,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009799518190355642,
+      "eval_loss": 11.932414054870605,
+      "eval_runtime": 8.7213,
+      "eval_samples_per_second": 295.597,
+      "eval_steps_per_second": 147.799,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011432771222081581,
+      "grad_norm": 0.010349428281188011,
+      "learning_rate": 0.00014,
+      "loss": 11.9306,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013066024253807521,
+      "grad_norm": 0.006527108605951071,
+      "learning_rate": 0.00016,
+      "loss": 11.9317,
+      "step": 8
+    },
+    {
+      "epoch": 0.0014699277285533461,
+      "grad_norm": 0.01932574063539505,
+      "learning_rate": 0.00018,
+      "loss": 11.9334,
+      "step": 9
+    },
+    {
+      "epoch": 0.0014699277285533461,
+      "eval_loss": 11.932388305664062,
+      "eval_runtime": 8.6392,
+      "eval_samples_per_second": 298.406,
+      "eval_steps_per_second": 149.203,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -63,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 354484224.0,
+  "total_flos": 1122533376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null