Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b17243c32965b355fc9765d5b59ada896b5f0165f17d38de8d655cb6481ad6a
+oid sha256:7419fd4a394616530e7e4016f5022773fdc92ae1296ca80f6a5bf0ec431163d4
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789fbaec49b413c9a763b4acf09bcfe86097890aba65f2d89aea0e3452c0430f
+oid sha256:beab14ec2e36624b41cc33fdbcffe6f82eedbb8b5d39ee4450e728ad70ebe203
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a18528153d6dd23c43c37e41b2823805f3d704c19995abc83179571246a672
+oid sha256:50cda8e50d81912588f6f70a1d216bbe3758254aaca8a8028195502492facac3
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:222a395289655e6330fa151479fc92b6da721e27fbeeddf74525fa4489d12a3a
+oid sha256:4f0f8419270f11766784e694dcbc34eca0a02509849c3c07787846a7c94e49c8
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92dfec00580cc49b39040eaf5b9c2db7f74dcfff57c6e3f25fc641f1656401d3
+oid sha256:0f3393c2f89a9ec8227a6ce9eac9a1da458cd93a68e5de7f895cbbf31d2fb7c5
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae40dca5e32a36e2a2c5a65c1db1aa929fb2ddcdc46c8721fde7e5f9e80b94bb
+oid sha256:0ca6f149c0c6a7e0afefc26ea78fb17812fa5dfd93b9034617986ba6b77fe358
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1728,
+  "epoch": 0.2304,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 227.245,
       "eval_steps_per_second": 7.128,
       "step": 27
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.8532243371009827,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.0382,
+      "step": 30
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 0.7470282912254333,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.0626,
+      "step": 33
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 0.885766327381134,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.0687,
+      "step": 36
+    },
+    {
+      "epoch": 0.2304,
+      "eval_loss": 2.036273717880249,
+      "eval_runtime": 4.5994,
+      "eval_samples_per_second": 228.727,
+      "eval_steps_per_second": 7.175,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.362994477694976e+16,
+  "total_flos": 5.810623995917107e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null