Training in progress, step 2040, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b6655782a983e665dba0e849d536995a49fc28327e1a340c6d0acb3e6a9346
+oid sha256:e47362b6d0eac1f82180e6b29ee3f7c2d915006bc065406131a0fd35b2efbbc1
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf5ba4c5bdffdca097a4cab622da35d4625e043ff5ff81b133e63498d06dbfc
+oid sha256:dd11da65ffb0d4570e59961b0c132d6bd8b1f1fdc0c2f1a395db947863533b9d
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c676bb33648ee9263046f9d978c9dc81390c0ac42995b13679bcd936e804701
+oid sha256:68d8d961de9fa331face7d8cad742caf1cb05dec24ac6128db0c9c0b06d4b11b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1288e563fd14386ce1f1f209b36f861a91ceda68715fc12dfb92acd5d04d997
+oid sha256:d1f92df614fc27cf99bd5eb65435800e9a0c33f53a2b39dfcb3917ef6db37df5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7227191413237924,
+  "epoch": 0.7298747763864043,
   "eval_steps": 500,
-  "global_step": 2020,
+  "global_step": 2040,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1623,14 +1623,30 @@
       "loss": 0.3982,
       "num_input_tokens_seen": 1366487,
       "step": 2020
+    },
+    {
+      "epoch": 0.7262969588550984,
+      "grad_norm": 0.2706156373023987,
+      "learning_rate": 5.4740608228980325e-05,
+      "loss": 0.3715,
+      "num_input_tokens_seen": 1374437,
+      "step": 2030
+    },
+    {
+      "epoch": 0.7298747763864043,
+      "grad_norm": 0.27796509861946106,
+      "learning_rate": 5.4025044722719145e-05,
+      "loss": 0.3981,
+      "num_input_tokens_seen": 1382038,
+      "step": 2040
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1366487,
+  "num_input_tokens_seen": 1382038,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.0727467028740096e+16,
+  "total_flos": 3.1077154102063104e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null