Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69459175c9d03bb8fe9e6c045cf88d7ac7fda52b2a81cf887875cb0a0feb5559
+oid sha256:5993c4c4d163ab954dfe832519aca623bdad9e0764b4903b237e97f672c90d35
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27c8120a3c07627b0df440a6457af50e95f961eb715039755d08556c3f4bdbe
+oid sha256:86b8d8a813490530fbba566b07f2c305142f58a531309e3c7b033a6ca7512e61
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d773c47027a459d5d8464ff6820fc3bbf26d05dc87232fa08fb08ce984c4e8fd
+oid sha256:adcef6bfbc179f9fd9fbbf02516b588576682520022367d731ffaa9dcbdda165
 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": 8.1518416368898e-05,
+  "epoch": 0.000163036832737796,
   "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": 17.853,
       "eval_steps_per_second": 8.926,
       "step": 3
+    },
+    {
+      "epoch": 0.00010869122182519734,
+      "grad_norm": 3.4636247158050537,
+      "learning_rate": 8e-05,
+      "loss": 5.373,
+      "step": 4
+    },
+    {
+      "epoch": 0.00013586402728149667,
+      "grad_norm": 2.4033591747283936,
+      "learning_rate": 0.0001,
+      "loss": 5.3612,
+      "step": 5
+    },
+    {
+      "epoch": 0.000163036832737796,
+      "grad_norm": 2.4599316120147705,
+      "learning_rate": 0.00012,
+      "loss": 5.3129,
+      "step": 6
+    },
+    {
+      "epoch": 0.000163036832737796,
+      "eval_loss": 5.394644737243652,
+      "eval_runtime": 882.0472,
+      "eval_samples_per_second": 17.568,
+      "eval_steps_per_second": 8.784,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1003322993541120.0,
+  "total_flos": 2054423272488960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null