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:ed642993e97b33c5f7a14097b44837631908708864c0e9abec4bd85033934166
+oid sha256:463be2c7e68d34fc4984ca7f4acd86f60c22e1cf44019b0a8471a7205fdbbc52
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffc3cb2e835a7fcd84f7c90321ba2c334b0bfa69800d1aaa9a2b1317e8c2351e
+oid sha256:ee2ac7ab5231e684ff75c3376a075da70c5a98db5dcf9e03853ec4d3c657f0c5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c6291480501dedfdd188a2dde82d0e9dc6215c3786cd8b8b61e96d2ad44a53
+oid sha256:ba235193674c62bf36a0508917933660b0c06a16abf8b712b7fc477352761722
 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": 0.00011592634812682343,
+  "epoch": 0.00023185269625364686,
   "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": 16.293,
       "eval_steps_per_second": 8.147,
       "step": 3
+    },
+    {
+      "epoch": 0.0001545684641690979,
+      "grad_norm": 3.170842409133911,
+      "learning_rate": 8e-05,
+      "loss": 7.6469,
+      "step": 4
+    },
+    {
+      "epoch": 0.00019321058021137238,
+      "grad_norm": 6.741440773010254,
+      "learning_rate": 0.0001,
+      "loss": 12.355,
+      "step": 5
+    },
+    {
+      "epoch": 0.00023185269625364686,
+      "grad_norm": 6.070605754852295,
+      "learning_rate": 0.00012,
+      "loss": 8.3175,
+      "step": 6
+    },
+    {
+      "epoch": 0.00023185269625364686,
+      "eval_loss": 2.427530527114868,
+      "eval_runtime": 669.0339,
+      "eval_samples_per_second": 16.288,
+      "eval_steps_per_second": 8.145,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 936530814173184.0,
+  "total_flos": 1832342897295360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null