Training in progress, step 1720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0c3e6d93a1441c7db78d93f7eb98fd49cc04f49449f2259d73e79e94b8e462f
+oid sha256:2571cd02811d646143de10022d9d61c8fbf4e91b2e1b761d5e95b98208a7f6ca
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b0a6c4bad52c1c9821d299c94aa36be9275ba88777c400aec09ddae498ac09
+oid sha256:a04b94f32120c904d17b5e7daf6e052525ae04f447d161e67e5960adc6e1237f
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3866c583342266c1b49a5646f3e71cb48f3e5caf6421bd9aef8d0ee6987d3924
+oid sha256:a642ee1476531cfd990fb5cb0edacdc4846648718d220ef0934d9434724daa35
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6def6f1c9d3b62ab3bc11afa81f32a34b7583be01c8ae04dd8eec288d3c0772c
+oid sha256:49f1e0333c6f78fccc02371feb195657c276bb422aba0842abe5ecaa76ddb2c6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6082289803220036,
+  "epoch": 0.6153846153846154,
   "eval_steps": 500,
-  "global_step": 1700,
+  "global_step": 1720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1367,14 +1367,30 @@
       "loss": 0.414,
       "num_input_tokens_seen": 1144688,
       "step": 1700
+    },
+    {
+      "epoch": 0.6118067978533095,
+      "grad_norm": 0.4987502098083496,
+      "learning_rate": 7.76386404293381e-05,
+      "loss": 0.4002,
+      "num_input_tokens_seen": 1151513,
+      "step": 1710
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.35515296459198,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 0.399,
+      "num_input_tokens_seen": 1159983,
+      "step": 1720
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1144688,
+  "num_input_tokens_seen": 1159983,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.5739990777954304e+16,
+  "total_flos": 2.6083921315313664e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null