Training in progress, step 1660, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10257b7014e9aac14048d4c25d8edac512b0d9b68ecd3b472b859543cdef14b
+oid sha256:ee715368403bed92f0597eabc44753fd00d49356f11cef1b3c8fb8c0804ae158
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9380c503afe8a570e3b4d2d7682a1be66462065c80d82ec8ac42553b0ce37b6
+oid sha256:208b124f35b0f1bb89c24aa5e442cf97e514521b89c0892c0bc2dd2ca24dcc7c
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4bae246be55e0c5c479cc3228ea806f5dad96bfbd997b22379ceb5166207ba
+oid sha256:ba8cf0f8aa521d1f1829b6d195f2417168669d9a3f3f5d0131830f8caf9a53ed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b5d3fd1283600a406407d024141f0dd9978a7bb53ae522b56311cc64308157
+oid sha256:f76a6b8811ac3433e0a8dcf8c698d49602a1ab3ba3e9478d0943f2dd2665d0e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5867620751341681,
+  "epoch": 0.59391771019678,
   "eval_steps": 500,
-  "global_step": 1640,
+  "global_step": 1660,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1319,14 +1319,30 @@
       "loss": 0.405,
       "num_input_tokens_seen": 1100973,
       "step": 1640
+    },
+    {
+      "epoch": 0.590339892665474,
+      "grad_norm": 0.29171282052993774,
+      "learning_rate": 8.19320214669052e-05,
+      "loss": 0.4103,
+      "num_input_tokens_seen": 1107805,
+      "step": 1650
+    },
+    {
+      "epoch": 0.59391771019678,
+      "grad_norm": 0.24154767394065857,
+      "learning_rate": 8.1216457960644e-05,
+      "loss": 0.3903,
+      "num_input_tokens_seen": 1115112,
+      "step": 1660
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1100973,
+  "num_input_tokens_seen": 1115112,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.4756994802755584e+16,
+  "total_flos": 2.5074930982404096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null