Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b206bf7ae06777ea7df3380ddd57e7f2e88e84e9842a567650151b9817fd57
+oid sha256:ed0c3952800e299afa73f4be122ae2384f3fc0bccc24db6376e4a3447760ae1e
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f65cbf80197b089897f183666453d559753fdb5669054d23773fbd4a1188864
+oid sha256:a8339e6538e71e112d2d55330f520aa2f93663d17d59cb014feb79ba923d94c8
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d622c5fb7bd558d55cdd7ea3c956fd06a0d8788be259d61032675ae3fa69edd6
+oid sha256:d3b2ed62d3c3041d929f4689e56812b00363ecda2ba4abac93da71f834cdd0c0
 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": 0.0017052721330112265,
+  "epoch": 0.003410544266022453,
   "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": 60.764,
       "eval_steps_per_second": 30.423,
       "step": 3
+    },
+    {
+      "epoch": 0.002273696177348302,
+      "grad_norm": 3.436891555786133,
+      "learning_rate": 8e-05,
+      "loss": 4.8595,
+      "step": 4
+    },
+    {
+      "epoch": 0.002842120221685377,
+      "grad_norm": 4.515559196472168,
+      "learning_rate": 0.0001,
+      "loss": 4.3636,
+      "step": 5
+    },
+    {
+      "epoch": 0.003410544266022453,
+      "grad_norm": 3.168912887573242,
+      "learning_rate": 0.00012,
+      "loss": 3.9756,
+      "step": 6
+    },
+    {
+      "epoch": 0.003410544266022453,
+      "eval_loss": 4.110952854156494,
+      "eval_runtime": 12.4679,
+      "eval_samples_per_second": 59.432,
+      "eval_steps_per_second": 29.756,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 146843338014720.0,
+  "total_flos": 293686676029440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null