Uploaded checkpoint-5000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254ebbd52547f6dea75030c04e0a2b055474bbc6442b19a967aefc6e9079ebe5
+oid sha256:db00791fe6be02cbf9d58bde5545dde203c803d64036669187cec6cf3eb19284
 size 119975656

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c0cb498833d020bbb0215ff2ae45922ef9b020686cdacea5e1ac6f32b37ea5
+oid sha256:b2d7f277b633524451fcf79452d7657c0be7ab33e9b11323f79bf0ffbd3e95da
 size 60477396

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633b157fbef241e6ec551fad6a854f5461dc50697c93a99c27418333ed23a3ff
+oid sha256:056c47f7cb4d7abe8a557a81ae1942cf3eb44d8487b4271bb8bc5c01f0d844ba
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc07b8b774f62e4a2e740a5aef480057a53613ea5c4ddc321e355c3850f172a7
+oid sha256:5a8b9195a0ab65d895e29be71344b338c125cf19b59f7afb36df3047db308f52
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0625,
+  "epoch": 0.125,
   "eval_steps": 2500,
-  "global_step": 2500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -29,6 +29,35 @@
       "eval_samples_per_second": 4.944,
       "eval_steps_per_second": 4.944,
       "step": 2500
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.314629316329956,
+      "learning_rate": 1.8551304347826088e-05,
+      "loss": 1.5222,
+      "step": 3000
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.6707098484039307,
+      "learning_rate": 1.7971594202898553e-05,
+      "loss": 1.4933,
+      "step": 4000
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.160583257675171,
+      "learning_rate": 1.7392463768115943e-05,
+      "loss": 1.5056,
+      "step": 5000
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4657692909240723,
+      "eval_runtime": 201.9515,
+      "eval_samples_per_second": 4.952,
+      "eval_steps_per_second": 4.952,
+      "step": 5000
     }
   ],
   "logging_steps": 1000,
@@ -36,7 +65,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2500,
-  "total_flos": 4.025531498496e+16,
+  "total_flos": 8.051062996992e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null