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:dcdc3b21dc5fbfda22520ee80ccef11ec7010e24828cb6ae9940dc583074911a
+oid sha256:ade2847a58db8b6423a5f4fa8082d97cfa75fd0f71d3775ae81d566b1f48ab5d
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a971786dcabdf98a0242515bf5990bd7ad6e71f7bac5f06a48c192c2fd0e83
+oid sha256:c77475810e399bb2c1186bbcd668401c86bf133df0c5589bdef1ad205621b206
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f7ced314baf64ed2febbea1a34ffbacbc38099cb191144ca5b001afd0de3f6
+oid sha256:8aa98b654a6ad98d9998c44f95a9ec59c7edf25202ad9a4080fb894c3b37d6e0
 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": 0.00046853037638606906,
+  "epoch": 0.0009370607527721381,
   "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": 47.673,
       "eval_steps_per_second": 23.845,
       "step": 3
+    },
+    {
+      "epoch": 0.0006247071685147587,
+      "grad_norm": 5.292506217956543,
+      "learning_rate": 8e-05,
+      "loss": 5.9008,
+      "step": 4
+    },
+    {
+      "epoch": 0.0007808839606434484,
+      "grad_norm": 5.258495807647705,
+      "learning_rate": 0.0001,
+      "loss": 6.1166,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009370607527721381,
+      "grad_norm": 5.323895454406738,
+      "learning_rate": 0.00012,
+      "loss": 6.7297,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009370607527721381,
+      "eval_loss": 5.9072957038879395,
+      "eval_runtime": 56.5863,
+      "eval_samples_per_second": 47.662,
+      "eval_steps_per_second": 23.84,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 72163654631424.0,
+  "total_flos": 144327309262848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null