Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd4e52e0a694b622356c32f19c184fc23d8fb9c1ffdc34dea61c4177d6dc872
+oid sha256:4d4c28eed7347f49ce3c2f49f2f5d02c32769707d9bac09e91540f9ce0bcdb7d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e4986a1abc988b386d23c1e81654596808f5f65c7d6014073a5a7531058d17
+oid sha256:3e30ea22c4fcf2cd59b920c61af983a6e3d0438f11af31107d6ce24cf8c03e76
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ecd1455bb3fc32a98fe70b8fb37696d4823754f4032a53a3810faccac9b739
+oid sha256:858ffaf5420905109f055dc370b50c9f0db5d0f1b10c2f4496d7349612d81ec4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c8f35d62ab0308ea4f3d434e6ddceeb2288fdcf54813dbe06805202a497865
+oid sha256:67ea7fdc27d3a55e20051ff7c0b0952cd04b9d78f6edb951d9b6865b402accbc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10922247252372176,
+  "epoch": 0.12287528158918698,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,28 @@
       "eval_samples_per_second": 35.224,
       "eval_steps_per_second": 8.806,
       "step": 800
+    },
+    {
+      "epoch": 0.11604887705645436,
+      "grad_norm": 81.04496002197266,
+      "learning_rate": 0.00025,
+      "loss": 9.0347,
+      "step": 850
+    },
+    {
+      "epoch": 0.12287528158918698,
+      "grad_norm": 125.09262084960938,
+      "learning_rate": 0.00025,
+      "loss": 9.0613,
+      "step": 900
+    },
+    {
+      "epoch": 0.12287528158918698,
+      "eval_loss": 2.4733426570892334,
+      "eval_runtime": 175.0699,
+      "eval_samples_per_second": 35.232,
+      "eval_steps_per_second": 8.808,
+      "step": 900
     }
   ],
   "logging_steps": 50,
@@ -210,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.829010669142016e+17,
+  "total_flos": 3.182637002784768e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null