Training in progress, step 56, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56491872a208ff227c56d67f1f1a29494d38977d18be9961d8f4c32526a2e6e4
+oid sha256:0ea14e80a0d5652668f7442a4f4757f36b7d66c3fdf65f7e642e8c3fce62a05e
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ba671e3027fba1c79fbf358ab0330c13044f9e72662f64a471aba358854afa
+oid sha256:d762612b78088c449b56dd2be896bf0a73f89f9e91ff767dd0d13323dff92ca1
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc9dbb623e3f171e33d9832b06d94b67f7dfbbcfe98e23137b132240f34a4be
+oid sha256:72bb0203fc4f241fbefdff46e3149502a543e3931c4ad5061ac8e4a3a4a9a8ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cec5e5f4f3cb8de86741361ea071d377a7169e2898cbb10708e17cdfc15a7dc
+oid sha256:8bcf905f092c501de6d33df5091b8a086f9e7304b56a4c771c8627db9d77566e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029955534753100865,
+  "epoch": 0.034948123878617676,
   "eval_steps": 8,
-  "global_step": 48,
+  "global_step": 56,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,28 @@
       "eval_samples_per_second": 9.399,
       "eval_steps_per_second": 4.699,
       "step": 48
+    },
+    {
+      "epoch": 0.03182775567516967,
+      "grad_norm": 0.3206414580345154,
+      "learning_rate": 0.00011785568947986367,
+      "loss": 0.8059,
+      "step": 51
+    },
+    {
+      "epoch": 0.033699976597238473,
+      "grad_norm": 0.330831378698349,
+      "learning_rate": 0.00010448648303505151,
+      "loss": 0.8291,
+      "step": 54
+    },
+    {
+      "epoch": 0.034948123878617676,
+      "eval_loss": 0.7632117867469788,
+      "eval_runtime": 574.4268,
+      "eval_samples_per_second": 9.397,
+      "eval_steps_per_second": 4.699,
+      "step": 56
     }
   ],
   "logging_steps": 3,
@@ -194,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5536922059276288e+17,
+  "total_flos": 2.9793075735822336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null