Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c00c3db6af84dc5c05265c262d1ccb86ad450de5c72199e9fee15585291e49d
+oid sha256:be3cb80b21de3a7061ea6a8b8aec6c1663a6055ae1eeae3400de929c197239ce
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1551c0c257786f3bac00486c33d78f92f1508dae546038a89ac49419271120
+oid sha256:8238e8748fbc6b599496ef00505acc11892101f0a04143c2974bfbb4a1277212
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e634e7f389aea7b6dd40a70664db0297f000009a50126be2db32cbd0235ea3d1
+oid sha256:9c43432f565aef530341d7cc48096f083d9fa5416d7585b979637cc324b8eefd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:741cd7c1d578b567afe0b32153af53c041328250902061a49c7bc1e60265dce0
+oid sha256:1a5e32ef43f1e5dcf3a02d7a877bcd517d98ac810aa46ac3eb2edaf28f847a7f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c75dc9ff6dbbb4c60ada37ec918b90ef8d15bda5636237f643dae0fcb170a6ba
+oid sha256:4308f530d8fcba647c33e505f76738d6105a4a84e1ca8ac4f3bdb3576ecd60ce
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14103174bc62255934f107137c101c4a55eab4b0d8988bc68e9e5c2a0a2ffc28
+oid sha256:4474b0eafad3150c96539dc0c61a8588ef903f62fb89096a2eef3b4ef508dba2
 size 15024

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": 0.06818181818181818,
+  "epoch": 0.13636363636363635,
   "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": 60.704,
       "eval_steps_per_second": 8.203,
       "step": 3
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 6.924163341522217,
+      "learning_rate": 8e-05,
+      "loss": 3.2663,
+      "step": 4
+    },
+    {
+      "epoch": 0.11363636363636363,
+      "grad_norm": 5.1875200271606445,
+      "learning_rate": 0.0001,
+      "loss": 3.6316,
+      "step": 5
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 5.6750168800354,
+      "learning_rate": 0.00012,
+      "loss": 2.8824,
+      "step": 6
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "eval_loss": 2.815485715866089,
+      "eval_runtime": 1.2233,
+      "eval_samples_per_second": 60.492,
+      "eval_steps_per_second": 8.175,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2470485052882944.0,
+  "total_flos": 4940970105765888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null