Training in progress, step 10200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1e13a85964ab8808bfc2b3469a4b76bee0bd96f331a8f39748e7032dc454ef7
+oid sha256:17ab87b52fe77b0aac85e5c4a2e2c19356beafbdb869980834b2c569fdd8dec2
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5ecf7fc68ce9f8cbd917b2dbb333c1ccbe8c2f546fdb594ee0191e94f36b9b
+oid sha256:a2ed17b033446d9fea3a59eba0464107af299cda4c40efa59a17995b6deae05b
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4453b9d90bd6b82be8e97e83b1ca59d9d5397ee45aa220e04d942e0915e20392
+oid sha256:d67b796360d477d8ece1783942ce085bd8d8c0c2c33afb30f69f41f2fc28a57a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acbeb015d4bc7f990999b8518ed60979c4618ba57aa1e5c62c07a2978164609d
+oid sha256:322071699a56ddf875d51673dd4754f2d337304fc1c0b6a592a283bd96af5a83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007436630611402585,
+  "epoch": 0.007585363223630638,
   "eval_steps": 2000,
-  "global_step": 10000,
+  "global_step": 10200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,13 @@
       "learning_rate": 1.9999891075382195e-05,
       "loss": 1.5554,
       "step": 10000
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.6852822303771973,
+      "learning_rate": 1.9999886669941987e-05,
+      "loss": 1.5473,
+      "step": 10200
     }
   ],
   "logging_steps": 200,
@@ -364,7 +371,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.3069591544338022e+17,
+  "total_flos": 1.3343348133096653e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null