Training in progress, step 62, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d16ed9ab9c4bfd98f29bf5f819bde84ba824e2c54a8db2353da1e7189ad0cb07
+oid sha256:31c49463f3821582d9d78755f5eb97a42b46bfdd8f9601d6971f4f497316456e
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2f01e8f872a1305ddc3fab247debab31a6dcb442e8b21b5af235956dfb761a
+oid sha256:255c08b2f79fe4bae4226d36f7cf03b9c43f1a10cbb716e63d3c74250abc8ff2
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b6d5df961b682e8c36756802b4652eb8397fb64bca4fff86cbd89ba5e2ecf2
+oid sha256:149f5934ccd723cc5ecad7bf2a9242c754be0eb33e2819fc4e2d0c12aedee181
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24fc915c71652348fb7923ecbe3044804dd3d0b1630ceca627060bf9ca491be1
+oid sha256:0d1b8a36fcf0317e6a9c8738d638639c228d4b5886701e2af2c36b54e118f8ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2515212981744422,
+  "epoch": 0.5030425963488844,
   "eval_steps": 31,
-  "global_step": 31,
+  "global_step": 62,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 5.902,
       "eval_steps_per_second": 0.738,
       "step": 31
+    },
+    {
+      "epoch": 0.26774847870182555,
+      "grad_norm": 5.427604675292969,
+      "learning_rate": 9.899623523104149e-05,
+      "loss": 2.4006,
+      "step": 33
+    },
+    {
+      "epoch": 0.2920892494929006,
+      "grad_norm": 7.537416458129883,
+      "learning_rate": 9.871850323926177e-05,
+      "loss": 2.7397,
+      "step": 36
+    },
+    {
+      "epoch": 0.31643002028397565,
+      "grad_norm": 8.674805641174316,
+      "learning_rate": 9.84073820189054e-05,
+      "loss": 2.4828,
+      "step": 39
+    },
+    {
+      "epoch": 0.3407707910750507,
+      "grad_norm": 8.167730331420898,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 2.5302,
+      "step": 42
+    },
+    {
+      "epoch": 0.36511156186612576,
+      "grad_norm": 10.937932014465332,
+      "learning_rate": 9.768584753741134e-05,
+      "loss": 2.3383,
+      "step": 45
+    },
+    {
+      "epoch": 0.3894523326572008,
+      "grad_norm": 3.8246636390686035,
+      "learning_rate": 9.727592877996585e-05,
+      "loss": 2.212,
+      "step": 48
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 4.667800426483154,
+      "learning_rate": 9.683360946241989e-05,
+      "loss": 2.3763,
+      "step": 51
+    },
+    {
+      "epoch": 0.4381338742393509,
+      "grad_norm": 4.990477561950684,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 2.3995,
+      "step": 54
+    },
+    {
+      "epoch": 0.46247464503042596,
+      "grad_norm": 9.09072494506836,
+      "learning_rate": 9.58530037192562e-05,
+      "loss": 2.545,
+      "step": 57
+    },
+    {
+      "epoch": 0.486815415821501,
+      "grad_norm": 5.338695049285889,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 2.3183,
+      "step": 60
+    },
+    {
+      "epoch": 0.5030425963488844,
+      "eval_loss": 0.5645254850387573,
+      "eval_runtime": 13.4155,
+      "eval_samples_per_second": 15.504,
+      "eval_steps_per_second": 1.938,
+      "step": 62
     }
   ],
   "logging_steps": 3,
@@ -112,7 +190,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.124536900209869e+16,
+  "total_flos": 8.249073800419738e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null