Training in progress, step 1700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9525a4c9388eba206599ad1083c9f04830f7c0993ba71f7249c50d3c13d194
+oid sha256:b0c3e6d93a1441c7db78d93f7eb98fd49cc04f49449f2259d73e79e94b8e462f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc517b5ef5e5fb65e842afb1ff46711a33890ca508092071a4522eec551c4860
+oid sha256:52b0a6c4bad52c1c9821d299c94aa36be9275ba88777c400aec09ddae498ac09
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2111ebc063da3a4cacd27c844d6c3c4ea5d6c8b4612b9ccfbb113e1022b25f1b
+oid sha256:3866c583342266c1b49a5646f3e71cb48f3e5caf6421bd9aef8d0ee6987d3924
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f33bde628cfaa59f6d1470858dd0b46ed4d4b40c45bae4e5eb4771b5d21f15
+oid sha256:6def6f1c9d3b62ab3bc11afa81f32a34b7583be01c8ae04dd8eec288d3c0772c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6010733452593918,
+  "epoch": 0.6082289803220036,
   "eval_steps": 500,
-  "global_step": 1680,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1351,14 +1351,30 @@
       "loss": 0.4015,
       "num_input_tokens_seen": 1129374,
       "step": 1680
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "grad_norm": 0.25734543800354004,
+      "learning_rate": 7.906976744186047e-05,
+      "loss": 0.3982,
+      "num_input_tokens_seen": 1136582,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6082289803220036,
+      "grad_norm": 0.263864666223526,
+      "learning_rate": 7.835420393559929e-05,
+      "loss": 0.414,
+      "num_input_tokens_seen": 1144688,
+      "step": 1700
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1129374,
+  "num_input_tokens_seen": 1144688,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.539563299769139e+16,
+  "total_flos": 2.5739990777954304e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null