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:d9429a5fb9c17559c2475a0f7015c0cb4c088ce76b349739e6dbc760a207a9c0
+oid sha256:d3f3075c6ca5892b290c9ec2e545ac7d548616a9ac143b0bc178fdf05cbadd08
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3b6b19b6daf202145b0acde255fd13f971d4e04c503afbdcde5de612e0c264
+oid sha256:9db6a4cd3e7ccd98ddd5254b3b696128958172c9d71379ce00423a7f73b4e34a
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d63550aef934dca682dbe4a2a94ff2b1a5fd333f064103ac7badea775ed97a9
+oid sha256:97a6caa870b6dc9a8c88458e23cc836a23db70a62629a6b0b992d3304258bab8
 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": 0.01892744479495268,
+  "epoch": 0.03785488958990536,
   "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": 31.416,
       "eval_steps_per_second": 15.943,
       "step": 3
+    },
+    {
+      "epoch": 0.025236593059936908,
+      "grad_norm": 29.974369049072266,
+      "learning_rate": 8e-05,
+      "loss": 11.5018,
+      "step": 4
+    },
+    {
+      "epoch": 0.031545741324921134,
+      "grad_norm": 27.482757568359375,
+      "learning_rate": 0.0001,
+      "loss": 11.4434,
+      "step": 5
+    },
+    {
+      "epoch": 0.03785488958990536,
+      "grad_norm": 32.79706954956055,
+      "learning_rate": 0.00012,
+      "loss": 8.8625,
+      "step": 6
+    },
+    {
+      "epoch": 0.03785488958990536,
+      "eval_loss": 6.5188446044921875,
+      "eval_runtime": 2.1634,
+      "eval_samples_per_second": 30.97,
+      "eval_steps_per_second": 15.716,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 162531632480256.0,
+  "total_flos": 350068131495936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null