Training in progress, step 820, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5209badae317ea0191985e9d2b0657c60495f0e245103e8da2f48bc30b76de0a
+oid sha256:c8266c5ce2daff311c6b7f99a82121a7d104c99faa78c3777323bc8fb69e449a
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0e1196eb242854610785eb717ce5d397736e1d72a99ab40f99e81408a87da4
+oid sha256:ba87eaf9f2c58fb6d0b0a1c2263a7833cdee74039a7d283d9e26e781413fe8ff
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d628c8ae931950a378a9db4ecb26be5d61a7980fd613e5a54938458cbc7fb5be
+oid sha256:f7526970e790becb006619bd780f0a177e541ca6e1e03e8171224f11d2b3cdea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d4e79f8eacfb7ad204b76c28b6041891ae49ddf9bc16a1dfb9c80df15148b7b
+oid sha256:38f6fcd2abad4866e3102113773264731c828e1e13009602886e42cd304ea258
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28622540250447226,
+  "epoch": 0.29338103756708406,
   "eval_steps": 500,
-  "global_step": 800,
+  "global_step": 820,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -647,14 +647,30 @@
       "loss": 0.4144,
       "num_input_tokens_seen": 535308,
       "step": 800
+    },
+    {
+      "epoch": 0.2898032200357782,
+      "grad_norm": 0.24462071061134338,
+      "learning_rate": 0.00014203935599284436,
+      "loss": 0.3984,
+      "num_input_tokens_seen": 542297,
+      "step": 810
+    },
+    {
+      "epoch": 0.29338103756708406,
+      "grad_norm": 0.4308456480503082,
+      "learning_rate": 0.0001413237924865832,
+      "loss": 0.4142,
+      "num_input_tokens_seen": 548183,
+      "step": 820
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 535308,
+  "num_input_tokens_seen": 548183,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.2037186537611264e+16,
+  "total_flos": 1.2326699820939264e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null