Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f701220ec81716a32a4d508f6822b66b2074ec86047f8e8f056187bdc1ab5c09
+oid sha256:4c40a931b938474e7ac0cc0462f5e739d4df2654285098b7df79361b9728b0d3
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b80e2f0ca9bc62e7fcaa505129fa793f6189b638ee9cff07d5b5b21cf2d026
+oid sha256:8d2bcdca872e1be0270e9898679d1483ea5519929122322feaecb3773f192304
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ad872338f15e42202b963c58b83ef6edf29994e347518dbc0914f0cdbb97b0
+oid sha256:fe05823d9b3a4ae96331974951fec2a9554e92db181f365ab8b362c7e4f414f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4510552f5f4688778b1947e191aa031f3e5576fcc244fe154f36949d3b59eca2
+oid sha256:4cae89a374497dc38b12678021ff8e8e13ee9363e1283e11bc6d982bc4b24c9f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5652951699463328,
+  "epoch": 0.5724508050089445,
   "eval_steps": 500,
-  "global_step": 1580,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1271,14 +1271,30 @@
       "loss": 0.4095,
       "num_input_tokens_seen": 1060584,
       "step": 1580
+    },
+    {
+      "epoch": 0.5688729874776386,
+      "grad_norm": 0.41065359115600586,
+      "learning_rate": 8.622540250447228e-05,
+      "loss": 0.3741,
+      "num_input_tokens_seen": 1066384,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5724508050089445,
+      "grad_norm": 0.3346722722053528,
+      "learning_rate": 8.55098389982111e-05,
+      "loss": 0.4068,
+      "num_input_tokens_seen": 1072956,
+      "step": 1600
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1060584,
+  "num_input_tokens_seen": 1072956,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.384878882214707e+16,
+  "total_flos": 2.412699141176525e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null