Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f003ad1572b0948a1909c01db905e9bdbf1d52f629c3560b771c8441851d7317
+oid sha256:1333272d1f08fbd814cb08f5a42792ab551fd91e277c3c6a5bbdeefc49d757a9
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437e9c6b9fce7489b966dda9b3668a45ad9738963f29ff26a7fbdb09f08d584c
+oid sha256:6a8025527339d1f138d5768ad99100aa9e96f0367b91a9c3cae18b7e6e3cfa44
 size 40570324

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d504d22c70365e955869229804fc73b5137014a18fd4465b41a6a55d0b2d969
+oid sha256:c4d4d519233b1d715f1e302ab6f44d45be958cf79d89096c5f483d5bae7b8096
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350b7a6f8159717ef2af74e68b6e9c8ed2775fab22debcfdf6f728bfa1bef4ad
+oid sha256:ff3806b6ededc075c4c89012dc49cff3604a5f3bc56562d72a0f71b6ec838696
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006218905472636816,
+  "epoch": 0.0012437810945273632,
   "eval_steps": 1000,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,13 +157,163 @@
       "learning_rate": 0.00015789473684210527,
       "loss": 1.694,
       "step": 25
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015578947368421052,
+      "loss": 1.4779,
+      "step": 26
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001536842105263158,
+      "loss": 1.638,
+      "step": 27
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015157894736842108,
+      "loss": 1.5519,
+      "step": 28
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014947368421052633,
+      "loss": 1.7623,
+      "step": 29
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 1.2871,
+      "step": 30
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 1.5806,
+      "step": 31
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 1.5541,
+      "step": 32
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 1.6991,
+      "step": 33
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 1.5331,
+      "step": 34
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 1.9143,
+      "step": 35
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 1.6051,
+      "step": 36
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 1.6311,
+      "step": 37
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 1.4711,
+      "step": 38
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 1.4644,
+      "step": 39
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 1.7623,
+      "step": 40
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 1.5635,
+      "step": 41
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012210526315789474,
+      "loss": 1.3194,
+      "step": 42
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012,
+      "loss": 1.3296,
+      "step": 43
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00011789473684210525,
+      "loss": 1.6656,
+      "step": 44
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 1.5584,
+      "step": 45
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001136842105263158,
+      "loss": 1.6557,
+      "step": 46
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00011157894736842105,
+      "loss": 1.4512,
+      "step": 47
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010947368421052633,
+      "loss": 1.4563,
+      "step": 48
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010736842105263158,
+      "loss": 1.4214,
+      "step": 49
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 1.6556,
+      "step": 50
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1278571417288704.0,
+  "total_flos": 2741329648189440.0,
   "trial_name": null,
   "trial_params": null
 }