Training in progress, step 3200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b17e3cc5361a6fb95a762276cf91289aa13131a8fbd9766fc3a4c840df560a
+oid sha256:1ffa24c6d65d6ebe046b12c298cf4ae161aa8f7a73a62399ba6434af84128daa
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0d3e162d54962a24152dbd5b6c2d74f4ab4f1cdf06ddc47eddf9d8b6d07ca2
+oid sha256:ecd655e3d91e89f6e1fa258974b79bf0d215f8ace68f3d365b99110b5abe49ce
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3c8b2c540004b798ef14a7898f64a9814643e8791bc9d21b3f9eb260faee38
+oid sha256:4c5ce141a264dd8520f51f3b5490a7f5208fde47774153324df63d2668f9a7d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b791cefec27286739c8a8bdafe733eef68db8d09837c7ad1df5edca79390d24b
+oid sha256:0770650b062be7cee981b3da10cdf7010bb9457e5bd03d190388904fc6d3b7aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0022309891834207756,
+  "epoch": 0.0023797217956488276,
   "eval_steps": 2000,
-  "global_step": 3000,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,13 @@
       "learning_rate": 1.9999990234026036e-05,
       "loss": 1.586,
       "step": 3000
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.8140385150909424,
+      "learning_rate": 1.9999988884312347e-05,
+      "loss": 1.6221,
+      "step": 3200
     }
   ],
   "logging_steps": 200,
@@ -119,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 3.905599131493171e+16,
+  "total_flos": 4.180089275793408e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null