Training in progress, step 10400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ab87b52fe77b0aac85e5c4a2e2c19356beafbdb869980834b2c569fdd8dec2
+oid sha256:e2bbb20e2e294c1c21192f562a8c629ebccc06ad6cd551b6f30c8e039ab4706c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ed17b033446d9fea3a59eba0464107af299cda4c40efa59a17995b6deae05b
+oid sha256:8ec42b92ca3eacb4edf3bf7f17472e3af6a7858800cee747ed46bbcad71a1cbe
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d67b796360d477d8ece1783942ce085bd8d8c0c2c33afb30f69f41f2fc28a57a
+oid sha256:e76cdf884e11761c200ac34b58dbb495717e6bde399a5bd34f22ad9223e288af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322071699a56ddf875d51673dd4754f2d337304fc1c0b6a592a283bd96af5a83
+oid sha256:267883072a6671c244f08bafb8d77a7436e4752bd5182174b7eeacf1d55aa425
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007585363223630638,
+  "epoch": 0.007734095835858689,
   "eval_steps": 2000,
-  "global_step": 10200,
+  "global_step": 10400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -364,6 +364,13 @@
       "learning_rate": 1.9999886669941987e-05,
       "loss": 1.5473,
       "step": 10200
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.603821039199829,
+      "learning_rate": 1.999988217717089e-05,
+      "loss": 1.5754,
+      "step": 10400
     }
   ],
   "logging_steps": 200,
@@ -371,7 +378,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.3343348133096653e+17,
+  "total_flos": 1.3591987236736205e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null