Training in progress, step 1820, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66e3856c23d2e195eb9ae7df24f61ed2a0f7d8ece6b19c7bd72766eca908cb01
+oid sha256:28ddd758223901c924b4a39d2b9adc57ddd56c3afa8fb973d5ec1abe128fca3b
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68513830fbf72ea70a1b5ed7fcd232e3c6856576863986c98edcb8f6ea26573a
+oid sha256:7e299b48ed8c7654ff0cc635ef02bd506683a7ab5a1e444aa5178257f66c3942
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c205b5697621377980e186326089bd957e1153b34f60a9fe258d7a714fbda01
+oid sha256:8cda418843404e2782fe6f5f002b4cdccdcb0443cc8062fcf67c27f24ef06b82
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e43231b8b3ce29488aa83c0d16aa2f601068365267d1bd1f2fa894d989bc15
+oid sha256:314de47bf6b1f60450b370f7a9cc3a90b8e2ec4f652380a82046763165a3b095
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6440071556350626,
+  "epoch": 0.6511627906976745,
   "eval_steps": 500,
-  "global_step": 1800,
+  "global_step": 1820,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1447,14 +1447,30 @@
       "loss": 0.3885,
       "num_input_tokens_seen": 1217841,
       "step": 1800
+    },
+    {
+      "epoch": 0.6475849731663685,
+      "grad_norm": 0.43780773878097534,
+      "learning_rate": 7.048300536672629e-05,
+      "loss": 0.3893,
+      "num_input_tokens_seen": 1225095,
+      "step": 1810
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "grad_norm": 0.381865918636322,
+      "learning_rate": 6.976744186046513e-05,
+      "loss": 0.3884,
+      "num_input_tokens_seen": 1234033,
+      "step": 1820
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1217841,
+  "num_input_tokens_seen": 1234033,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.738494341603533e+16,
+  "total_flos": 2.7749044315736064e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null