Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1333272d1f08fbd814cb08f5a42792ab551fd91e277c3c6a5bbdeefc49d757a9
+oid sha256:661995d6fcb6405e7c8ad56ab888ddeab69ea83d2429fbf08b080ea5756f3eb6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8025527339d1f138d5768ad99100aa9e96f0367b91a9c3cae18b7e6e3cfa44
+oid sha256:aea908c6d7c1a8815a3a34246a07b139da722c669d76b45323ce9a8b68a35787
 size 40570324

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d4d519233b1d715f1e302ab6f44d45be958cf79d89096c5f483d5bae7b8096
+oid sha256:d7d8f7f8e1a76d94091cc701a4a00cc6fd2a3c1a746e29e297276a305cc6801f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff3806b6ededc075c4c89012dc49cff3604a5f3bc56562d72a0f71b6ec838696
+oid sha256:2cb9069cac0762cbe9eda0682450e4a822dfd10b17c5f7335626649d1825624d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012437810945273632,
+  "epoch": 0.0018656716417910447,
   "eval_steps": 1000,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,13 +307,163 @@
       "learning_rate": 0.00010526315789473685,
       "loss": 1.6556,
       "step": 50
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 1.5774,
+      "step": 51
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010105263157894738,
+      "loss": 1.5624,
+      "step": 52
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.894736842105263e-05,
+      "loss": 1.0224,
+      "step": 53
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.68421052631579e-05,
+      "loss": 1.5792,
+      "step": 54
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 1.6203,
+      "step": 55
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.263157894736843e-05,
+      "loss": 1.6145,
+      "step": 56
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.052631578947369e-05,
+      "loss": 1.5488,
+      "step": 57
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.842105263157894e-05,
+      "loss": 1.7138,
+      "step": 58
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.631578947368421e-05,
+      "loss": 1.5731,
+      "step": 59
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 1.2584,
+      "step": 60
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 1.4644,
+      "step": 61
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8e-05,
+      "loss": 1.4227,
+      "step": 62
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 1.4762,
+      "step": 63
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 1.6393,
+      "step": 64
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 1.6137,
+      "step": 65
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 1.4132,
+      "step": 66
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 1.9143,
+      "step": 67
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 1.2177,
+      "step": 68
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 1.6103,
+      "step": 69
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 1.3548,
+      "step": 70
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 1.6381,
+      "step": 71
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.894736842105263e-05,
+      "loss": 1.6296,
+      "step": 72
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.68421052631579e-05,
+      "loss": 1.6071,
+      "step": 73
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 1.7263,
+      "step": 74
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 1.5891,
+      "step": 75
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2741329648189440.0,
+  "total_flos": 4183967298846720.0,
   "trial_name": null,
   "trial_params": null
 }