Training in progress, step 1840, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ddd758223901c924b4a39d2b9adc57ddd56c3afa8fb973d5ec1abe128fca3b
+oid sha256:0a35a2af3ea2b94599601250de962941256a5efcad327f119611098c5b727b81
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e299b48ed8c7654ff0cc635ef02bd506683a7ab5a1e444aa5178257f66c3942
+oid sha256:6b232299157051b5378f91d7d702fbb841c1ef5ad7312b7cdc673c0431537e5b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cda418843404e2782fe6f5f002b4cdccdcb0443cc8062fcf67c27f24ef06b82
+oid sha256:0eb529110b293466c5e24700957fd7c44cccfdb2c6358ccd14c0e45847418541
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314de47bf6b1f60450b370f7a9cc3a90b8e2ec4f652380a82046763165a3b095
+oid sha256:d98628c593bf963c980bce85f986fc776c13df4f931f97e7900bb98fb04dfa21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6511627906976745,
+  "epoch": 0.6583184257602862,
   "eval_steps": 500,
-  "global_step": 1820,
+  "global_step": 1840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1463,14 +1463,30 @@
       "loss": 0.3884,
       "num_input_tokens_seen": 1234033,
       "step": 1820
+    },
+    {
+      "epoch": 0.6547406082289803,
+      "grad_norm": 0.4573935866355896,
+      "learning_rate": 6.905187835420393e-05,
+      "loss": 0.4199,
+      "num_input_tokens_seen": 1241707,
+      "step": 1830
+    },
+    {
+      "epoch": 0.6583184257602862,
+      "grad_norm": 0.2445441335439682,
+      "learning_rate": 6.833631484794277e-05,
+      "loss": 0.3934,
+      "num_input_tokens_seen": 1248683,
+      "step": 1840
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1234033,
+  "num_input_tokens_seen": 1248683,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.7749044315736064e+16,
+  "total_flos": 2.8078471080843264e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null