Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81a186f4e2db0ff269dad5cae1d69750c4da7104086b9809a59b674e5a3cc64
+oid sha256:fb3bff090ac21a9f79bdec3f19adea904a1c9048bf0b740fcd27a3dee2a3fb99
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:571eeebf27a66d00e2abf2acf6722179764481c236d54326a069f1cf6f272f8c
+oid sha256:87e267c8551e92bec1c0d95190b0e7d8b2184a65730d3c55852532864c0cb462
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf86cd5b19b8056a2759fc36b0c4f0323fb9c04403c19df65bcd5311b20dea5
+oid sha256:6d785e1f858f9b24c91f6a197613a9f3b03b25de4e2921242c11b806523a9c2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000487685930260912,
+  "epoch": 0.000975371860521824,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 20.292,
       "eval_steps_per_second": 10.15,
       "step": 3
+    },
+    {
+      "epoch": 0.0006502479070145493,
+      "grad_norm": 0.17509125173091888,
+      "learning_rate": 8e-05,
+      "loss": 0.7986,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008128098837681866,
+      "grad_norm": 0.22162194550037384,
+      "learning_rate": 0.0001,
+      "loss": 0.8673,
+      "step": 5
+    },
+    {
+      "epoch": 0.000975371860521824,
+      "grad_norm": 0.20332558453083038,
+      "learning_rate": 0.00012,
+      "loss": 0.8076,
+      "step": 6
+    },
+    {
+      "epoch": 0.000975371860521824,
+      "eval_loss": 0.826266884803772,
+      "eval_runtime": 127.8557,
+      "eval_samples_per_second": 20.265,
+      "eval_steps_per_second": 10.136,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 949861251809280.0,
+  "total_flos": 1978877607936000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null