Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5ce6ed8e2430ec842b4115b90ae3d0d6e379c6fe2c66e54fc145bd06c7abd1
+oid sha256:e609611ebab773e129de2b02bae00dc2a78c5d8f338b89f97a6f05230dbf70c5
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254aa79d73407eebabfd5213784dc5d4a89647c5be76eaa6933654b1d0b83420
+oid sha256:0e9303c04860ea0c913209b671a95265bdfff5f8aee8045c62db1a36bb8bdd71
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248924ed5d78bd8edc8d3afd4f26ba1e09189a0e5b560e090cc38b1c31910681
+oid sha256:106282343697551818085781983c88bfc9ede264fece121f95753ca09a0e5b18
 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": 0.001171760570256811,
+  "epoch": 0.002343521140513622,
   "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": 11.294,
       "eval_steps_per_second": 5.647,
       "step": 3
+    },
+    {
+      "epoch": 0.001562347427009081,
+      "grad_norm": 32.677711486816406,
+      "learning_rate": 8e-05,
+      "loss": 37.3262,
+      "step": 4
+    },
+    {
+      "epoch": 0.0019529342837613514,
+      "grad_norm": 53.797515869140625,
+      "learning_rate": 0.0001,
+      "loss": 33.2911,
+      "step": 5
+    },
+    {
+      "epoch": 0.002343521140513622,
+      "grad_norm": 50.63685607910156,
+      "learning_rate": 0.00012,
+      "loss": 32.4459,
+      "step": 6
+    },
+    {
+      "epoch": 0.002343521140513622,
+      "eval_loss": 6.371692180633545,
+      "eval_runtime": 95.4974,
+      "eval_samples_per_second": 11.288,
+      "eval_steps_per_second": 5.644,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 732937158918144.0,
+  "total_flos": 1343718124683264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null