Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7fae7fd7b7097062d598f7e39173c3be076fd38a518e39695d38611e173e616
+oid sha256:9af15712c0a3794e9c1d0a4647d80824418034babf4a3bb3b12da49cbbd4591f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:503f7d70ed87b1b9116e473527994a439b84afd2922b7fe9e9c8ca07d7ce6011
+oid sha256:6d3ec05dc2a420e6b6f433431a7210a9f8b5b939c17e338af4fcfd032a22568f
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86d923ec2b558f5a06989b166ae0440604c2186db868315a47068592d49bc28
+oid sha256:0cf5ebe402c7dce97f342040c0f0b95bb1430955f10f0a17d27e4f469c8ee708
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f64992c1d4407619f94c2bf93637b1c409030cc8fc813c98252feafc612aaf
+oid sha256:84612bd3f396f7cad2af4e3f356db64f473c832d56581301631417d37a7919d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028622540250447227,
+  "epoch": 0.03577817531305903,
   "eval_steps": 500,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -71,14 +71,30 @@
       "loss": 0.4642,
       "num_input_tokens_seen": 53439,
       "step": 80
+    },
+    {
+      "epoch": 0.03220035778175313,
+      "grad_norm": 0.4074145257472992,
+      "learning_rate": 0.00019355992844364938,
+      "loss": 0.4431,
+      "num_input_tokens_seen": 59366,
+      "step": 90
+    },
+    {
+      "epoch": 0.03577817531305903,
+      "grad_norm": 0.372760534286499,
+      "learning_rate": 0.0001928443649373882,
+      "loss": 0.4824,
+      "num_input_tokens_seen": 66414,
+      "step": 100
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 53439,
+  "num_input_tokens_seen": 66414,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1201654395942912.0,
+  "total_flos": 1493416326131712.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null