Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c7eea7e50de6e251744f3ee790ca4a6387d47e8ce7452440f7051839c84729
+oid sha256:28d06a5ae849e5eafa966876580c2e0e9ff7c6b8b5e195728a8c697108ebe5c0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f251d52ad5464ead9d205feac28656ff564122f188fb78b487d868fc3f516f2
+oid sha256:ca9d832ae35a9d313b54125833c1bfa7d1138929a7f50961bff7d5fdbc8aa682
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a090bc482ef5f1b83af8f13fdd6e9fe2b0babec66f75c50ea84e39461e78f9
+oid sha256:dae627a7d2298122bff578106eebf3a91e3c4a65f4b6f1686a626ab036cc9c37
 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": 0.00029182879377431906,
+  "epoch": 0.0005836575875486381,
   "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": 10.137,
       "eval_steps_per_second": 5.07,
       "step": 3
+    },
+    {
+      "epoch": 0.0003891050583657588,
+      "grad_norm": 13.882640838623047,
+      "learning_rate": 8e-05,
+      "loss": 29.1269,
+      "step": 4
+    },
+    {
+      "epoch": 0.00048638132295719845,
+      "grad_norm": 41.90673065185547,
+      "learning_rate": 0.0001,
+      "loss": 32.9532,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005836575875486381,
+      "grad_norm": 25.500226974487305,
+      "learning_rate": 0.00012,
+      "loss": 28.3286,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005836575875486381,
+      "eval_loss": 6.694687843322754,
+      "eval_runtime": 432.8707,
+      "eval_samples_per_second": 10.001,
+      "eval_steps_per_second": 5.001,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 488624772612096.0,
+  "total_flos": 977249545224192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null