Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a2ad8642cbaad3d2adfa9740eaf32d9ab3f79236f46fbb2f49b5c121af31aa
+oid sha256:755e3bb881c2cebe2408f71967bbbd8d5aaeba1775eee58d820a2b2705c4f322
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b88bd19824e2842f5ce84e0b5d69f7450ac7b7d55418fc1b2b62a0326606677
+oid sha256:9a9568e402f9ff409ca76cc7c73fe3bdaabc1c99d2f693067e5262f8c8966fb1
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3c556c10c7731d2efcd3349657c843bb58ecb920ff933caa3eff158c72a43d
+oid sha256:2f3ce663a654f1c3a028d29de6ae324384473759d92d2769648e71c2472a6c44
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de01b002e41057a41033f4225dfd7cc46944d877c0e63a66a14ddbdb8127d468
+oid sha256:6c8ead9b14defda85ea166a9f438954d73e821d54f912b5c1a0327a6e7667837
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1db5b31743ec24cc9401ba91995ad70e091a5020ca18016cfe89274e556097
+oid sha256:f85ad1440f05d71f340e84ef1dd13d68f034d5b55fcdcecb2eb1431877a2bbe7
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ed3448a79dc798d88b7326bc4ad6f807686ef4333a099c03fbcd045d0e232c
+oid sha256:c0b74d0ea1674edd7d998f628112d9051f4bd1ae1bc2aa10369d7245d8a08657
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.576,
+  "epoch": 0.6336,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 227.913,
       "eval_steps_per_second": 7.149,
       "step": 90
+    },
+    {
+      "epoch": 0.5952,
+      "grad_norm": 0.8635654449462891,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.04,
+      "step": 93
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 0.8225715756416321,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.0424,
+      "step": 96
+    },
+    {
+      "epoch": 0.6336,
+      "grad_norm": 0.9119483232498169,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.9926,
+      "step": 99
+    },
+    {
+      "epoch": 0.6336,
+      "eval_loss": 1.9934889078140259,
+      "eval_runtime": 4.5921,
+      "eval_samples_per_second": 229.087,
+      "eval_steps_per_second": 7.186,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4526559989792768e+17,
+  "total_flos": 1.59741895080149e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null