Training in progress, step 1760, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd26cfe9b646210c60d4811af8b70f3f54f489bec1b95bff978b4f03ee10cad5
+oid sha256:8e48abae2f95ba4e9bedb869c8329abdb510faed9a580042f44d70a7f83dfedb
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9d7727bb468ce33cc85c85dbc8bf7fca3716b4e134b773d14e3a430add12064
+oid sha256:a06145c0e4a87e3902e14e18d5fe445b63ed952afc1411bcb27aeb5ea7f93d1c
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2754616b85cea2ec4918640d230c479a914b3143b7c0af235eb6e00c51de30f
+oid sha256:2f4d63e8a027423d577ea7af105cf9dfa0eceb5cbaa55c3d1be9537ed2066e33
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5eb12cc8f462347c54ae45e967712ebfb182e1bce4f798acee1ab55a15db33
+oid sha256:3a4891f7777b5838c1e2791421eb76185eb3d423f14cc978012d40df3e76c8ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6225402504472272,
+  "epoch": 0.629695885509839,
   "eval_steps": 500,
-  "global_step": 1740,
+  "global_step": 1760,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1399,14 +1399,30 @@
       "loss": 0.4031,
       "num_input_tokens_seen": 1175665,
       "step": 1740
+    },
+    {
+      "epoch": 0.6261180679785331,
+      "grad_norm": 0.33866697549819946,
+      "learning_rate": 7.477638640429339e-05,
+      "loss": 0.412,
+      "num_input_tokens_seen": 1181930,
+      "step": 1750
+    },
+    {
+      "epoch": 0.629695885509839,
+      "grad_norm": 0.2600657045841217,
+      "learning_rate": 7.40608228980322e-05,
+      "loss": 0.3975,
+      "num_input_tokens_seen": 1189185,
+      "step": 1760
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1175665,
+  "num_input_tokens_seen": 1189185,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.643655411602432e+16,
+  "total_flos": 2.674057117160448e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null