Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d0731536a3a48e8e3c7579aca873d033891aaa08cfa4eb2ea2796e4e7f0bc8
+oid sha256:0b28e929e31402580bc7714ece765bebaf6232a77f1945b6acd6f9edd64c2dbf
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce253faa9ea9f6e1d8be2edc42dd7ecc908a76bd824e497a22a7cd796f1d5508
+oid sha256:f2dd9c2c5c4ed94606f74a8ebe5edae84a5ff2ee2612b72c0fde25ccd64cf9f9
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3dabe00fea1d741e6ac4c6d741f948e913732a663cdf14e06018bb9855b7957
+oid sha256:1b02cb45f4d7dbcf1f3bbd1da580bee2c1c4946401fd6dcc2d96aa004cddd97d
 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": 0.014035087719298246,
+  "epoch": 0.028070175438596492,
   "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": 57.546,
       "eval_steps_per_second": 28.773,
       "step": 3
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 1.060206651687622,
+      "learning_rate": 8e-05,
+      "loss": 2.3413,
+      "step": 4
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 0.8521826863288879,
+      "learning_rate": 0.0001,
+      "loss": 1.9854,
+      "step": 5
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 0.784907341003418,
+      "learning_rate": 0.00012,
+      "loss": 1.8668,
+      "step": 6
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "eval_loss": 1.9630398750305176,
+      "eval_runtime": 1.5778,
+      "eval_samples_per_second": 57.042,
+      "eval_steps_per_second": 28.521,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 126286395604992.0,
+  "total_flos": 264600066981888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null