Training in progress, step 2140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43137dcf390023aa5067a211d636996954c9ca898ec9ee8555959a85c62e7bfe
+oid sha256:2b31cd1bacf359ded93b1a975a832f43cf8275d8876e0472c643b229fff2eb00
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:790c8e59662f43ac84c519659bdaa05cca33252fe4eb1a8e529222ba4b475a33
+oid sha256:e963850275f272c22ef0a3706fe2ae328531160ce5f9a82b5cc306c0bdd72573
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8438c68a449ee9662d6e071a644f8c20e7783415ed2d9e7fbb32cddadbcbcc
+oid sha256:0002b99f842540feaa883ef0561d8d2638b1009ac9f8f241ca4c7a7d22a87a41
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b6fe67887c52dbf0f864a623d737d0bb3a2cd6bd534693b6fd8d589c2a836a
+oid sha256:3b36f7fc3da668a866fd41d662c3dd39a222899bdb3fe635785c3fffd4983ac1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7584973166368515,
+  "epoch": 0.7656529516994633,
   "eval_steps": 500,
-  "global_step": 2120,
+  "global_step": 2140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1703,14 +1703,30 @@
       "loss": 0.3879,
       "num_input_tokens_seen": 1437151,
       "step": 2120
+    },
+    {
+      "epoch": 0.7620751341681574,
+      "grad_norm": 0.2736769914627075,
+      "learning_rate": 4.758497316636852e-05,
+      "loss": 0.3994,
+      "num_input_tokens_seen": 1443666,
+      "step": 2130
+    },
+    {
+      "epoch": 0.7656529516994633,
+      "grad_norm": 0.46681609749794006,
+      "learning_rate": 4.686940966010734e-05,
+      "loss": 0.3754,
+      "num_input_tokens_seen": 1449724,
+      "step": 2140
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1437151,
+  "num_input_tokens_seen": 1449724,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.231645084645581e+16,
+  "total_flos": 3.259917321626419e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null